diff --git a/.gitattributes b/.gitattributes
index 70898625f0e2789ba55c622119da6ebc985092e6..68b07250c3610e23e139719c5bc8b8f19214aae4 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -1,199 +1,38 @@
-DeepSeek-R1-Distill-Qwen-32B_4bit/model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_6bit_mixed/model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_8bit/model-00003-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_2bit_mixed/model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_3bit_uniform/model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_4bit/model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_8bit_mixed/model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_8bit/model-00001-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00001-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00005-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_3bit_mixed/model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_6bit_uniform/model-00002-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_6bit_uniform/model-00005-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00002-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_4bit_mixed/model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_4bit/model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_6bit_uniform/model-00004-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_8bit_mixed/model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_8bit/model-00002-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00006-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00007-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00011-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_3bit_mixed/model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_6bit_mixed/model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_6bit_uniform/model-00001-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_8bit/model-00005-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_8bit/model-00006-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_2bit_mixed/model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_4bit_mixed/model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_8bit/model-00007-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00008-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00010-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_3bit_mixed/model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_3bit_uniform/model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_3bit_uniform/model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_6bit_mixed/model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_6bit_uniform/model-00006-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00003-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00009-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00013-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_2bit_mixed/model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_4bit_mixed/model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_4bit/model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_6bit_uniform/model-00003-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_8bit_mixed/model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_8bit/model-00004-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00004-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00012-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-32B_4bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-32B_bfloat16/tokenizer.json filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_4,8_mixed/model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_4,8_mixed/model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_4,8_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_4,8_mixed/model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_4,8_mixed/model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00004-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00001-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00019-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00013-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00016-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00024-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00012-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/tokenizer.json filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00005-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00003-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00021-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00025-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00017-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00020-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00018-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00006-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00009-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00002-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00026-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00023-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00014-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00011-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00008-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_8bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00007-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00015-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_3bit/model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_3bit/model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_3bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_3bit/model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_2,6_mixed/model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_2,6_mixed/model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_2,6_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_2,6_mixed/model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00010-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float32/model-00022-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float16/tokenizer.json filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float16/model-00010-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float16/model-00007-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float16/model-00002-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float16/model-00009-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float16/model-00008-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float16/model-00011-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float16/model-00006-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float16/model-00003-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_6bit/model-00002-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_6bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_6bit/model-00003-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_6bit/model-00006-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_6bit/model-00005-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_6bit/model-00004-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_6bit/model-00001-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_3,4_mixed/model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_3,4_mixed/model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_3,4_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_3,4_mixed/model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_3,6_mixed/model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_3,6_mixed/model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_3,6_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_3,6_mixed/model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float16/model-00005-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float16/model-00013-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float16/model-00001-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float16/model-00012-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B_float16/model-00004-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-4bit/model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-4bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-6bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-4bit/model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-6bit/model-00006-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-4bit/model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-4bit/model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-6bit/model-00002-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-6bit/model-00003-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-6bit/model-00005-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-6bit/model-00004-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-6bit/model-00001-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-3bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-3bit/model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-3bit/model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-3bit/model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-float16/tokenizer.json filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-float16/model-00010-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-float16/model-00007-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-float16/model-00002-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-float16/model-00008-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-float16/model-00011-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-float16/model-00009-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-float16/model-00006-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-float16/model-00003-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-float16/model-00005-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-float16/model-00012-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-float16/model-00001-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-float16/model-00013-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-float16/model-00004-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00010-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00007-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-bfloat16/tokenizer.json filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00002-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00008-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00009-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00011-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00006-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00003-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00005-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00013-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-8bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00012-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00001-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00004-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-8bit/model-00005-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-8bit/model-00007-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-8bit/model-00001-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-8bit/model-00004-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-8bit/model-00002-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-8bit/model-00006-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-8bit/model-00003-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
-DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
diff --git a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/config.json b/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/config.json
deleted file mode 100644
index b0b83d44724403ed68786d8f2330d57dd6970756..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/config.json
+++ /dev/null
@@ -1,4021 +0,0 @@
-{
- "architectures": [
- "Qwen2ForCausalLM"
- ],
- "attention_dropout": 0.0,
- "bos_token_id": 151643,
- "eos_token_id": 151643,
- "hidden_act": "silu",
- "hidden_size": 5120,
- "initializer_range": 0.02,
- "intermediate_size": 27648,
- "max_position_embeddings": 131072,
- "max_window_layers": 64,
- "model_type": "qwen2",
- "num_attention_heads": 40,
- "num_hidden_layers": 64,
- "num_key_value_heads": 8,
- "quantization": {
- "group_size": 64,
- "bits": null,
- "model.embed_tokens": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.0.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.0.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.0.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.0.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.0.self_attn.rope": false,
- "model.layers.0.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.0.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.0.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.0.input_layernorm": false,
- "model.layers.0.post_attention_layernorm": false,
- "model.layers.1.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.1.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.1.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.1.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.1.self_attn.rope": false,
- "model.layers.1.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.1.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.1.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.1.input_layernorm": false,
- "model.layers.1.post_attention_layernorm": false,
- "model.layers.2.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.2.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.2.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.2.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.2.self_attn.rope": false,
- "model.layers.2.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.2.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.2.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.2.input_layernorm": false,
- "model.layers.2.post_attention_layernorm": false,
- "model.layers.3.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.3.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.3.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.3.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.3.self_attn.rope": false,
- "model.layers.3.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.3.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.3.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.3.input_layernorm": false,
- "model.layers.3.post_attention_layernorm": false,
- "model.layers.4.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.4.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.4.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.4.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.4.self_attn.rope": false,
- "model.layers.4.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.4.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.4.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.4.input_layernorm": false,
- "model.layers.4.post_attention_layernorm": false,
- "model.layers.5.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.5.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.5.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.5.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.5.self_attn.rope": false,
- "model.layers.5.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.5.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.5.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.5.input_layernorm": false,
- "model.layers.5.post_attention_layernorm": false,
- "model.layers.6.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.6.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.6.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.6.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.6.self_attn.rope": false,
- "model.layers.6.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.6.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.6.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.6.input_layernorm": false,
- "model.layers.6.post_attention_layernorm": false,
- "model.layers.7.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.7.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.7.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.7.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.7.self_attn.rope": false,
- "model.layers.7.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.7.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.7.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.7.input_layernorm": false,
- "model.layers.7.post_attention_layernorm": false,
- "model.layers.8.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.8.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.8.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.8.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.8.self_attn.rope": false,
- "model.layers.8.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.8.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.8.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.8.input_layernorm": false,
- "model.layers.8.post_attention_layernorm": false,
- "model.layers.9.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.9.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.9.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.9.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.9.self_attn.rope": false,
- "model.layers.9.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.9.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.9.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.9.input_layernorm": false,
- "model.layers.9.post_attention_layernorm": false,
- "model.layers.10.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.10.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.10.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.10.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.10.self_attn.rope": false,
- "model.layers.10.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.10.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.10.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.10.input_layernorm": false,
- "model.layers.10.post_attention_layernorm": false,
- "model.layers.11.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.11.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.11.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.11.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.11.self_attn.rope": false,
- "model.layers.11.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.11.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.11.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.11.input_layernorm": false,
- "model.layers.11.post_attention_layernorm": false,
- "model.layers.12.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.12.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.12.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.12.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.12.self_attn.rope": false,
- "model.layers.12.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.12.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.12.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.12.input_layernorm": false,
- "model.layers.12.post_attention_layernorm": false,
- "model.layers.13.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.13.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.13.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.13.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.13.self_attn.rope": false,
- "model.layers.13.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.13.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.13.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.13.input_layernorm": false,
- "model.layers.13.post_attention_layernorm": false,
- "model.layers.14.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.14.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.14.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.14.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.14.self_attn.rope": false,
- "model.layers.14.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.14.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.14.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.14.input_layernorm": false,
- "model.layers.14.post_attention_layernorm": false,
- "model.layers.15.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.15.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.15.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.15.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.15.self_attn.rope": false,
- "model.layers.15.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.15.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.15.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.15.input_layernorm": false,
- "model.layers.15.post_attention_layernorm": false,
- "model.layers.16.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.16.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.16.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.16.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.16.self_attn.rope": false,
- "model.layers.16.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.16.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.16.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.16.input_layernorm": false,
- "model.layers.16.post_attention_layernorm": false,
- "model.layers.17.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.17.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.17.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.17.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.17.self_attn.rope": false,
- "model.layers.17.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.17.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.17.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.17.input_layernorm": false,
- "model.layers.17.post_attention_layernorm": false,
- "model.layers.18.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.18.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.18.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.18.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.18.self_attn.rope": false,
- "model.layers.18.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.18.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.18.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.18.input_layernorm": false,
- "model.layers.18.post_attention_layernorm": false,
- "model.layers.19.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.19.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.19.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.19.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.19.self_attn.rope": false,
- "model.layers.19.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.19.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.19.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.19.input_layernorm": false,
- "model.layers.19.post_attention_layernorm": false,
- "model.layers.20.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.20.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.20.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.20.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.20.self_attn.rope": false,
- "model.layers.20.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.20.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.20.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.20.input_layernorm": false,
- "model.layers.20.post_attention_layernorm": false,
- "model.layers.21.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.21.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.21.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.21.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.21.self_attn.rope": false,
- "model.layers.21.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.21.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.21.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.21.input_layernorm": false,
- "model.layers.21.post_attention_layernorm": false,
- "model.layers.22.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.22.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.22.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.22.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.22.self_attn.rope": false,
- "model.layers.22.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.22.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.22.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.22.input_layernorm": false,
- "model.layers.22.post_attention_layernorm": false,
- "model.layers.23.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.23.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.23.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.23.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.23.self_attn.rope": false,
- "model.layers.23.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.23.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.23.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.23.input_layernorm": false,
- "model.layers.23.post_attention_layernorm": false,
- "model.layers.24.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.24.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.24.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.24.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.24.self_attn.rope": false,
- "model.layers.24.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.24.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.24.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.24.input_layernorm": false,
- "model.layers.24.post_attention_layernorm": false,
- "model.layers.25.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.25.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.25.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.25.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.25.self_attn.rope": false,
- "model.layers.25.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.25.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.25.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.25.input_layernorm": false,
- "model.layers.25.post_attention_layernorm": false,
- "model.layers.26.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.26.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.26.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.26.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.26.self_attn.rope": false,
- "model.layers.26.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.26.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.26.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.26.input_layernorm": false,
- "model.layers.26.post_attention_layernorm": false,
- "model.layers.27.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.27.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.27.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.27.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.27.self_attn.rope": false,
- "model.layers.27.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.27.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.27.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.27.input_layernorm": false,
- "model.layers.27.post_attention_layernorm": false,
- "model.layers.28.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.28.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.28.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.28.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.28.self_attn.rope": false,
- "model.layers.28.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.28.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.28.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.28.input_layernorm": false,
- "model.layers.28.post_attention_layernorm": false,
- "model.layers.29.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.29.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.29.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.29.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.29.self_attn.rope": false,
- "model.layers.29.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.29.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.29.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.29.input_layernorm": false,
- "model.layers.29.post_attention_layernorm": false,
- "model.layers.30.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.30.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.30.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.30.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.30.self_attn.rope": false,
- "model.layers.30.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.30.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.30.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.30.input_layernorm": false,
- "model.layers.30.post_attention_layernorm": false,
- "model.layers.31.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.31.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.31.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.31.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.31.self_attn.rope": false,
- "model.layers.31.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.31.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.31.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.31.input_layernorm": false,
- "model.layers.31.post_attention_layernorm": false,
- "model.layers.32.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.32.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.32.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.32.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.32.self_attn.rope": false,
- "model.layers.32.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.32.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.32.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.32.input_layernorm": false,
- "model.layers.32.post_attention_layernorm": false,
- "model.layers.33.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.33.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.33.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.33.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.33.self_attn.rope": false,
- "model.layers.33.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.33.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.33.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.33.input_layernorm": false,
- "model.layers.33.post_attention_layernorm": false,
- "model.layers.34.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.34.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.34.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.34.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.34.self_attn.rope": false,
- "model.layers.34.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.34.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.34.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.34.input_layernorm": false,
- "model.layers.34.post_attention_layernorm": false,
- "model.layers.35.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.35.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.35.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.35.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.35.self_attn.rope": false,
- "model.layers.35.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.35.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.35.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.35.input_layernorm": false,
- "model.layers.35.post_attention_layernorm": false,
- "model.layers.36.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.36.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.36.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.36.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.36.self_attn.rope": false,
- "model.layers.36.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.36.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.36.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.36.input_layernorm": false,
- "model.layers.36.post_attention_layernorm": false,
- "model.layers.37.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.37.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.37.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.37.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.37.self_attn.rope": false,
- "model.layers.37.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.37.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.37.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.37.input_layernorm": false,
- "model.layers.37.post_attention_layernorm": false,
- "model.layers.38.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.38.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.38.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.38.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.38.self_attn.rope": false,
- "model.layers.38.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.38.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.38.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.38.input_layernorm": false,
- "model.layers.38.post_attention_layernorm": false,
- "model.layers.39.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.39.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.39.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.39.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.39.self_attn.rope": false,
- "model.layers.39.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.39.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.39.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.39.input_layernorm": false,
- "model.layers.39.post_attention_layernorm": false,
- "model.layers.40.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.40.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.40.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.40.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.40.self_attn.rope": false,
- "model.layers.40.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.40.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.40.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.40.input_layernorm": false,
- "model.layers.40.post_attention_layernorm": false,
- "model.layers.41.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.41.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.41.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.41.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.41.self_attn.rope": false,
- "model.layers.41.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.41.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.41.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.41.input_layernorm": false,
- "model.layers.41.post_attention_layernorm": false,
- "model.layers.42.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.42.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.42.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.42.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.42.self_attn.rope": false,
- "model.layers.42.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.42.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.42.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.42.input_layernorm": false,
- "model.layers.42.post_attention_layernorm": false,
- "model.layers.43.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.43.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.43.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.43.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.43.self_attn.rope": false,
- "model.layers.43.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.43.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.43.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.43.input_layernorm": false,
- "model.layers.43.post_attention_layernorm": false,
- "model.layers.44.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.44.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.44.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.44.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.44.self_attn.rope": false,
- "model.layers.44.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.44.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.44.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.44.input_layernorm": false,
- "model.layers.44.post_attention_layernorm": false,
- "model.layers.45.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.45.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.45.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.45.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.45.self_attn.rope": false,
- "model.layers.45.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.45.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.45.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.45.input_layernorm": false,
- "model.layers.45.post_attention_layernorm": false,
- "model.layers.46.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.46.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.46.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.46.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.46.self_attn.rope": false,
- "model.layers.46.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.46.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.46.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.46.input_layernorm": false,
- "model.layers.46.post_attention_layernorm": false,
- "model.layers.47.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.47.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.47.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.47.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.47.self_attn.rope": false,
- "model.layers.47.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.47.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.47.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.47.input_layernorm": false,
- "model.layers.47.post_attention_layernorm": false,
- "model.layers.48.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.48.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.48.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.48.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.48.self_attn.rope": false,
- "model.layers.48.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.48.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.48.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.48.input_layernorm": false,
- "model.layers.48.post_attention_layernorm": false,
- "model.layers.49.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.49.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.49.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.49.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.49.self_attn.rope": false,
- "model.layers.49.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.49.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.49.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.49.input_layernorm": false,
- "model.layers.49.post_attention_layernorm": false,
- "model.layers.50.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.50.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.50.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.50.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.50.self_attn.rope": false,
- "model.layers.50.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.50.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.50.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.50.input_layernorm": false,
- "model.layers.50.post_attention_layernorm": false,
- "model.layers.51.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.51.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.51.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.51.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.51.self_attn.rope": false,
- "model.layers.51.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.51.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.51.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.51.input_layernorm": false,
- "model.layers.51.post_attention_layernorm": false,
- "model.layers.52.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.52.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.52.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.52.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.52.self_attn.rope": false,
- "model.layers.52.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.52.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.52.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.52.input_layernorm": false,
- "model.layers.52.post_attention_layernorm": false,
- "model.layers.53.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.53.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.53.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.53.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.53.self_attn.rope": false,
- "model.layers.53.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.53.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.53.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.53.input_layernorm": false,
- "model.layers.53.post_attention_layernorm": false,
- "model.layers.54.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.54.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.54.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.54.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.54.self_attn.rope": false,
- "model.layers.54.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.54.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.54.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.54.input_layernorm": false,
- "model.layers.54.post_attention_layernorm": false,
- "model.layers.55.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.55.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.55.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.55.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.55.self_attn.rope": false,
- "model.layers.55.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.55.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.55.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.55.input_layernorm": false,
- "model.layers.55.post_attention_layernorm": false,
- "model.layers.56.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.56.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.56.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.56.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.56.self_attn.rope": false,
- "model.layers.56.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.56.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.56.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.56.input_layernorm": false,
- "model.layers.56.post_attention_layernorm": false,
- "model.layers.57.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.57.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.57.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.57.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.57.self_attn.rope": false,
- "model.layers.57.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.57.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.57.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.57.input_layernorm": false,
- "model.layers.57.post_attention_layernorm": false,
- "model.layers.58.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.58.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.58.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.58.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.58.self_attn.rope": false,
- "model.layers.58.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.58.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.58.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.58.input_layernorm": false,
- "model.layers.58.post_attention_layernorm": false,
- "model.layers.59.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.59.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.59.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.59.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.59.self_attn.rope": false,
- "model.layers.59.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.59.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.59.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.59.input_layernorm": false,
- "model.layers.59.post_attention_layernorm": false,
- "model.layers.60.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.60.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.60.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.60.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.60.self_attn.rope": false,
- "model.layers.60.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.60.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.60.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.60.input_layernorm": false,
- "model.layers.60.post_attention_layernorm": false,
- "model.layers.61.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.61.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.61.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.61.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.61.self_attn.rope": false,
- "model.layers.61.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.61.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.61.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.61.input_layernorm": false,
- "model.layers.61.post_attention_layernorm": false,
- "model.layers.62.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.62.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.62.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.62.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.62.self_attn.rope": false,
- "model.layers.62.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.62.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.62.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.62.input_layernorm": false,
- "model.layers.62.post_attention_layernorm": false,
- "model.layers.63.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.63.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.63.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.63.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.63.self_attn.rope": false,
- "model.layers.63.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.63.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.63.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.63.input_layernorm": false,
- "model.layers.63.post_attention_layernorm": false,
- "model.norm": false,
- "lm_head": {
- "group_size": 64,
- "bits": 4
- }
- },
- "quantization_config": {
- "group_size": 64,
- "bits": null,
- "model.embed_tokens": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.0.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.0.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.0.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.0.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.0.self_attn.rope": false,
- "model.layers.0.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.0.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.0.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.0.input_layernorm": false,
- "model.layers.0.post_attention_layernorm": false,
- "model.layers.1.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.1.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.1.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.1.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.1.self_attn.rope": false,
- "model.layers.1.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.1.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.1.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.1.input_layernorm": false,
- "model.layers.1.post_attention_layernorm": false,
- "model.layers.2.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.2.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.2.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.2.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.2.self_attn.rope": false,
- "model.layers.2.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.2.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.2.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.2.input_layernorm": false,
- "model.layers.2.post_attention_layernorm": false,
- "model.layers.3.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.3.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.3.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.3.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.3.self_attn.rope": false,
- "model.layers.3.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.3.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.3.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.3.input_layernorm": false,
- "model.layers.3.post_attention_layernorm": false,
- "model.layers.4.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.4.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.4.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.4.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.4.self_attn.rope": false,
- "model.layers.4.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.4.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.4.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.4.input_layernorm": false,
- "model.layers.4.post_attention_layernorm": false,
- "model.layers.5.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.5.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.5.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.5.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.5.self_attn.rope": false,
- "model.layers.5.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.5.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.5.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.5.input_layernorm": false,
- "model.layers.5.post_attention_layernorm": false,
- "model.layers.6.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.6.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.6.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.6.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.6.self_attn.rope": false,
- "model.layers.6.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.6.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.6.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.6.input_layernorm": false,
- "model.layers.6.post_attention_layernorm": false,
- "model.layers.7.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.7.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.7.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.7.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.7.self_attn.rope": false,
- "model.layers.7.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.7.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.7.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.7.input_layernorm": false,
- "model.layers.7.post_attention_layernorm": false,
- "model.layers.8.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.8.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.8.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.8.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.8.self_attn.rope": false,
- "model.layers.8.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.8.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.8.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.8.input_layernorm": false,
- "model.layers.8.post_attention_layernorm": false,
- "model.layers.9.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.9.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.9.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.9.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.9.self_attn.rope": false,
- "model.layers.9.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.9.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.9.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.9.input_layernorm": false,
- "model.layers.9.post_attention_layernorm": false,
- "model.layers.10.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.10.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.10.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.10.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.10.self_attn.rope": false,
- "model.layers.10.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.10.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.10.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.10.input_layernorm": false,
- "model.layers.10.post_attention_layernorm": false,
- "model.layers.11.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.11.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.11.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.11.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.11.self_attn.rope": false,
- "model.layers.11.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.11.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.11.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.11.input_layernorm": false,
- "model.layers.11.post_attention_layernorm": false,
- "model.layers.12.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.12.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.12.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.12.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.12.self_attn.rope": false,
- "model.layers.12.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.12.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.12.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.12.input_layernorm": false,
- "model.layers.12.post_attention_layernorm": false,
- "model.layers.13.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.13.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.13.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.13.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.13.self_attn.rope": false,
- "model.layers.13.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.13.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.13.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.13.input_layernorm": false,
- "model.layers.13.post_attention_layernorm": false,
- "model.layers.14.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.14.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.14.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.14.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.14.self_attn.rope": false,
- "model.layers.14.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.14.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.14.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.14.input_layernorm": false,
- "model.layers.14.post_attention_layernorm": false,
- "model.layers.15.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.15.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.15.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.15.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.15.self_attn.rope": false,
- "model.layers.15.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.15.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.15.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.15.input_layernorm": false,
- "model.layers.15.post_attention_layernorm": false,
- "model.layers.16.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.16.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.16.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.16.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.16.self_attn.rope": false,
- "model.layers.16.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.16.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.16.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.16.input_layernorm": false,
- "model.layers.16.post_attention_layernorm": false,
- "model.layers.17.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.17.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.17.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.17.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.17.self_attn.rope": false,
- "model.layers.17.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.17.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.17.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.17.input_layernorm": false,
- "model.layers.17.post_attention_layernorm": false,
- "model.layers.18.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.18.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.18.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.18.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.18.self_attn.rope": false,
- "model.layers.18.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.18.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.18.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.18.input_layernorm": false,
- "model.layers.18.post_attention_layernorm": false,
- "model.layers.19.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.19.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.19.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.19.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.19.self_attn.rope": false,
- "model.layers.19.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.19.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.19.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.19.input_layernorm": false,
- "model.layers.19.post_attention_layernorm": false,
- "model.layers.20.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.20.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.20.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.20.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.20.self_attn.rope": false,
- "model.layers.20.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.20.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.20.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.20.input_layernorm": false,
- "model.layers.20.post_attention_layernorm": false,
- "model.layers.21.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.21.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.21.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.21.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.21.self_attn.rope": false,
- "model.layers.21.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.21.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.21.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.21.input_layernorm": false,
- "model.layers.21.post_attention_layernorm": false,
- "model.layers.22.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.22.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.22.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.22.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.22.self_attn.rope": false,
- "model.layers.22.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.22.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.22.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.22.input_layernorm": false,
- "model.layers.22.post_attention_layernorm": false,
- "model.layers.23.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.23.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.23.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.23.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.23.self_attn.rope": false,
- "model.layers.23.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.23.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.23.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.23.input_layernorm": false,
- "model.layers.23.post_attention_layernorm": false,
- "model.layers.24.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.24.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.24.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.24.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.24.self_attn.rope": false,
- "model.layers.24.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.24.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.24.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.24.input_layernorm": false,
- "model.layers.24.post_attention_layernorm": false,
- "model.layers.25.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.25.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.25.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.25.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.25.self_attn.rope": false,
- "model.layers.25.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.25.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.25.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.25.input_layernorm": false,
- "model.layers.25.post_attention_layernorm": false,
- "model.layers.26.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.26.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.26.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.26.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.26.self_attn.rope": false,
- "model.layers.26.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.26.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.26.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.26.input_layernorm": false,
- "model.layers.26.post_attention_layernorm": false,
- "model.layers.27.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.27.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.27.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.27.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.27.self_attn.rope": false,
- "model.layers.27.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.27.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.27.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.27.input_layernorm": false,
- "model.layers.27.post_attention_layernorm": false,
- "model.layers.28.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.28.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.28.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.28.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.28.self_attn.rope": false,
- "model.layers.28.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.28.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.28.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.28.input_layernorm": false,
- "model.layers.28.post_attention_layernorm": false,
- "model.layers.29.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.29.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.29.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.29.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.29.self_attn.rope": false,
- "model.layers.29.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.29.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.29.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.29.input_layernorm": false,
- "model.layers.29.post_attention_layernorm": false,
- "model.layers.30.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.30.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.30.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.30.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.30.self_attn.rope": false,
- "model.layers.30.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.30.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.30.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.30.input_layernorm": false,
- "model.layers.30.post_attention_layernorm": false,
- "model.layers.31.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.31.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.31.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.31.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.31.self_attn.rope": false,
- "model.layers.31.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.31.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.31.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.31.input_layernorm": false,
- "model.layers.31.post_attention_layernorm": false,
- "model.layers.32.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.32.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.32.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.32.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.32.self_attn.rope": false,
- "model.layers.32.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.32.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.32.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.32.input_layernorm": false,
- "model.layers.32.post_attention_layernorm": false,
- "model.layers.33.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.33.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.33.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.33.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.33.self_attn.rope": false,
- "model.layers.33.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.33.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.33.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.33.input_layernorm": false,
- "model.layers.33.post_attention_layernorm": false,
- "model.layers.34.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.34.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.34.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.34.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.34.self_attn.rope": false,
- "model.layers.34.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.34.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.34.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.34.input_layernorm": false,
- "model.layers.34.post_attention_layernorm": false,
- "model.layers.35.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.35.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.35.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.35.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.35.self_attn.rope": false,
- "model.layers.35.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.35.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.35.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.35.input_layernorm": false,
- "model.layers.35.post_attention_layernorm": false,
- "model.layers.36.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.36.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.36.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.36.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.36.self_attn.rope": false,
- "model.layers.36.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.36.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.36.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.36.input_layernorm": false,
- "model.layers.36.post_attention_layernorm": false,
- "model.layers.37.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.37.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.37.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.37.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.37.self_attn.rope": false,
- "model.layers.37.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.37.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.37.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.37.input_layernorm": false,
- "model.layers.37.post_attention_layernorm": false,
- "model.layers.38.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.38.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.38.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.38.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.38.self_attn.rope": false,
- "model.layers.38.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.38.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.38.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.38.input_layernorm": false,
- "model.layers.38.post_attention_layernorm": false,
- "model.layers.39.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.39.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.39.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.39.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.39.self_attn.rope": false,
- "model.layers.39.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.39.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.39.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.39.input_layernorm": false,
- "model.layers.39.post_attention_layernorm": false,
- "model.layers.40.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.40.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.40.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.40.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.40.self_attn.rope": false,
- "model.layers.40.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.40.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.40.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.40.input_layernorm": false,
- "model.layers.40.post_attention_layernorm": false,
- "model.layers.41.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.41.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.41.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.41.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.41.self_attn.rope": false,
- "model.layers.41.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.41.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.41.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.41.input_layernorm": false,
- "model.layers.41.post_attention_layernorm": false,
- "model.layers.42.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.42.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.42.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.42.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.42.self_attn.rope": false,
- "model.layers.42.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.42.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.42.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.42.input_layernorm": false,
- "model.layers.42.post_attention_layernorm": false,
- "model.layers.43.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.43.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.43.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.43.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.43.self_attn.rope": false,
- "model.layers.43.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.43.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.43.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.43.input_layernorm": false,
- "model.layers.43.post_attention_layernorm": false,
- "model.layers.44.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.44.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.44.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.44.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.44.self_attn.rope": false,
- "model.layers.44.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.44.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.44.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.44.input_layernorm": false,
- "model.layers.44.post_attention_layernorm": false,
- "model.layers.45.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.45.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.45.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.45.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.45.self_attn.rope": false,
- "model.layers.45.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.45.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.45.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.45.input_layernorm": false,
- "model.layers.45.post_attention_layernorm": false,
- "model.layers.46.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.46.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.46.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.46.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.46.self_attn.rope": false,
- "model.layers.46.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.46.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.46.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.46.input_layernorm": false,
- "model.layers.46.post_attention_layernorm": false,
- "model.layers.47.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.47.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.47.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.47.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.47.self_attn.rope": false,
- "model.layers.47.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.47.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.47.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.47.input_layernorm": false,
- "model.layers.47.post_attention_layernorm": false,
- "model.layers.48.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.48.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.48.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.48.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.48.self_attn.rope": false,
- "model.layers.48.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.48.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.48.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.48.input_layernorm": false,
- "model.layers.48.post_attention_layernorm": false,
- "model.layers.49.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.49.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.49.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.49.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.49.self_attn.rope": false,
- "model.layers.49.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.49.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.49.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.49.input_layernorm": false,
- "model.layers.49.post_attention_layernorm": false,
- "model.layers.50.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.50.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.50.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.50.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.50.self_attn.rope": false,
- "model.layers.50.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.50.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.50.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.50.input_layernorm": false,
- "model.layers.50.post_attention_layernorm": false,
- "model.layers.51.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.51.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.51.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.51.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.51.self_attn.rope": false,
- "model.layers.51.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.51.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.51.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.51.input_layernorm": false,
- "model.layers.51.post_attention_layernorm": false,
- "model.layers.52.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.52.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.52.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.52.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.52.self_attn.rope": false,
- "model.layers.52.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.52.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.52.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.52.input_layernorm": false,
- "model.layers.52.post_attention_layernorm": false,
- "model.layers.53.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.53.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.53.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.53.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.53.self_attn.rope": false,
- "model.layers.53.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.53.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.53.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.53.input_layernorm": false,
- "model.layers.53.post_attention_layernorm": false,
- "model.layers.54.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.54.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.54.self_attn.v_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.54.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.54.self_attn.rope": false,
- "model.layers.54.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.54.mlp.down_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.54.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.54.input_layernorm": false,
- "model.layers.54.post_attention_layernorm": false,
- "model.layers.55.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.55.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.55.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.55.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.55.self_attn.rope": false,
- "model.layers.55.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.55.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.55.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.55.input_layernorm": false,
- "model.layers.55.post_attention_layernorm": false,
- "model.layers.56.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.56.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.56.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.56.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.56.self_attn.rope": false,
- "model.layers.56.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.56.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.56.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.56.input_layernorm": false,
- "model.layers.56.post_attention_layernorm": false,
- "model.layers.57.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.57.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.57.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.57.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.57.self_attn.rope": false,
- "model.layers.57.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.57.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.57.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.57.input_layernorm": false,
- "model.layers.57.post_attention_layernorm": false,
- "model.layers.58.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.58.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.58.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.58.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.58.self_attn.rope": false,
- "model.layers.58.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.58.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.58.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.58.input_layernorm": false,
- "model.layers.58.post_attention_layernorm": false,
- "model.layers.59.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.59.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.59.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.59.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.59.self_attn.rope": false,
- "model.layers.59.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.59.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.59.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.59.input_layernorm": false,
- "model.layers.59.post_attention_layernorm": false,
- "model.layers.60.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.60.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.60.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.60.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.60.self_attn.rope": false,
- "model.layers.60.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.60.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.60.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.60.input_layernorm": false,
- "model.layers.60.post_attention_layernorm": false,
- "model.layers.61.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.61.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.61.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.61.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.61.self_attn.rope": false,
- "model.layers.61.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.61.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.61.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.61.input_layernorm": false,
- "model.layers.61.post_attention_layernorm": false,
- "model.layers.62.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.62.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.62.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.62.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.62.self_attn.rope": false,
- "model.layers.62.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.62.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.62.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.62.input_layernorm": false,
- "model.layers.62.post_attention_layernorm": false,
- "model.layers.63.self_attn.q_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.63.self_attn.k_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.63.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.63.self_attn.o_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.63.self_attn.rope": false,
- "model.layers.63.mlp.gate_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.63.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.63.mlp.up_proj": {
- "group_size": 64,
- "bits": 2
- },
- "model.layers.63.input_layernorm": false,
- "model.layers.63.post_attention_layernorm": false,
- "model.norm": false,
- "lm_head": {
- "group_size": 64,
- "bits": 4
- }
- },
- "rms_norm_eps": 1e-05,
- "rope_theta": 1000000.0,
- "sliding_window": 131072,
- "tie_word_embeddings": false,
- "torch_dtype": "bfloat16",
- "transformers_version": "4.43.1",
- "use_cache": true,
- "use_sliding_window": false,
- "vocab_size": 152064
-}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00001-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00001-of-00003.safetensors
deleted file mode 100644
index 525ce1e468c5669bf7eaf2f8b0103414a808e02c..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00001-of-00003.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1fd0562b9c91b2672857fdfb6c8f64d34545b54754352a4289ca624a3b51ec7c
-size 5366073812
diff --git a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00002-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00002-of-00003.safetensors
deleted file mode 100644
index e6d0cf8a2604829bbb3f125e8daaa60a66490945..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00002-of-00003.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3cf3baaa2b1173fdade1e377c93b05e81ed99b04d2ac4f19b55fe0d8f7da429e
-size 5303704839
diff --git a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00003-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00003-of-00003.safetensors
deleted file mode 100644
index 7d22cc2025e5a4693ce277f4b8489ec0438b060f..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00003-of-00003.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:36559b03cc3bdb442c6e20d45cfe0550b43ba4c1c8bdc1dc9f33aaf4fbb1265b
-size 940057505
diff --git a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model.safetensors.index.json
deleted file mode 100644
index e5a5e26859fcef0de641200508c152d88d92d3d2..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model.safetensors.index.json
+++ /dev/null
@@ -1,1678 +0,0 @@
-{
- "metadata": {
- "total_size": 11609647104
- },
- "weight_map": {
- "lm_head.biases": "model-00003-of-00003.safetensors",
- "lm_head.scales": "model-00003-of-00003.safetensors",
- "lm_head.weight": "model-00003-of-00003.safetensors",
- "model.embed_tokens.biases": "model-00001-of-00003.safetensors",
- "model.embed_tokens.scales": "model-00001-of-00003.safetensors",
- "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.22.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.22.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.22.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.22.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.23.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.23.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.23.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.23.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.23.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.23.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.23.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.23.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.24.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.24.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.24.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.24.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.24.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.24.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.24.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.24.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.24.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.24.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.24.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.24.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.24.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.24.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.24.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.24.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.24.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.25.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.25.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.25.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.25.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.25.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.25.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.25.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.25.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.25.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.25.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.25.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.25.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.25.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.25.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.25.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.25.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.25.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.26.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.26.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.26.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.26.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.26.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.26.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.26.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.26.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.26.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.26.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.26.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.26.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.26.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.26.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.26.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.26.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.26.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.27.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.27.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.27.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.27.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.27.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.27.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.27.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.27.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.27.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.27.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.27.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.27.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.27.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.27.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.27.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.27.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.27.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.28.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.28.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.28.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.28.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.28.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.28.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.28.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.28.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.28.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.28.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.28.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.28.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.28.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.28.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.28.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.28.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.28.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.29.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.29.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.29.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.29.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.29.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.29.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.29.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.29.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.29.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.29.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.29.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.29.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.29.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.29.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.29.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.29.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.29.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.40.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.47.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.47.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.47.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.47.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.47.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.47.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.47.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.47.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.47.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.48.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.48.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.48.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.48.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.48.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.48.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.48.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.48.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.48.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.48.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.48.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.49.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.49.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.49.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.49.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.49.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.49.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.49.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.49.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.49.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.49.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.49.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.49.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.49.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.49.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.49.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.49.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.49.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.49.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.49.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.49.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.49.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.49.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.49.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.49.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.49.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.49.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.50.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.50.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.50.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.50.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.50.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.50.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.50.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.50.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.50.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.50.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.50.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.50.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.50.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.50.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.50.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.50.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.50.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.50.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.50.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.50.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.50.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.50.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.50.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.50.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.50.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.50.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.51.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.51.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.51.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.51.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.51.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.51.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.51.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.51.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.51.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.51.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.51.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.51.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.51.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.51.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.51.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.51.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.51.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.51.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.51.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.51.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.51.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.51.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.51.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.51.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.51.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.51.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.52.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.52.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.52.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.52.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.52.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.52.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.52.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.52.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.52.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.52.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.52.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.52.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.52.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.52.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.52.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.52.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.52.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.52.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.52.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.52.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.52.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.52.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.52.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.52.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.52.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.52.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.53.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.53.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.53.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.53.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.53.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.53.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.53.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.53.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.53.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.53.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.53.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.53.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.53.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.53.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.53.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.53.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.53.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.53.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.53.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.53.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.53.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.53.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.53.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.53.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.53.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.53.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.54.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.54.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.54.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.54.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.54.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.54.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.54.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.54.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.54.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.54.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.54.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.54.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.54.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.54.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.54.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.54.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.54.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.54.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.54.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.54.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.54.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.54.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.54.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.54.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.54.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.54.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.55.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.55.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.55.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.55.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.55.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.55.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.55.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.55.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.55.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.55.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.55.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.55.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.55.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.55.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.55.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.55.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.55.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.55.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.55.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.55.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.55.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.55.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.55.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.55.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.55.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.55.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.56.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.56.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.56.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.56.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.56.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.56.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.56.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.56.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.56.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.56.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.56.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.56.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.56.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.56.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.56.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.56.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.56.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.56.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.56.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.56.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.56.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.56.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.56.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.56.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.56.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.56.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.57.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.57.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.57.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.57.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.57.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.57.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.57.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.57.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.57.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.57.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.57.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.57.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.57.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.57.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.57.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.57.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.57.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.57.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.57.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.57.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.57.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.57.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.57.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.57.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.57.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.57.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.58.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.58.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.58.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.58.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.58.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.58.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.58.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.58.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.58.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.58.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.58.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.58.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.58.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.58.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.58.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.58.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.58.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.58.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.58.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.58.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.58.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.58.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.58.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.58.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.58.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.58.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.59.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.59.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.59.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.59.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.59.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.59.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.59.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.59.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.59.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.59.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.59.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.59.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.59.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.59.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.59.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.59.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.59.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.59.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.59.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.59.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.59.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.59.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.59.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.59.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.59.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.59.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.60.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.60.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.60.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.60.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.60.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.60.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.60.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.60.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.60.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.60.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.60.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.60.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.60.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.60.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.60.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.60.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.60.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.60.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.60.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.60.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.60.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.60.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.60.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.60.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.60.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.60.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.61.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.61.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.61.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.61.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.61.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.61.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.61.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.61.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.61.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.61.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.61.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.61.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.61.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.61.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.61.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.61.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.61.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.61.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.62.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.norm.weight": "model-00003-of-00003.safetensors"
- }
-}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/config.json b/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/config.json
deleted file mode 100644
index c25d6bc33782d800fdf5ada7960ebe5c9a778dd5..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/config.json
+++ /dev/null
@@ -1,4021 +0,0 @@
-{
- "architectures": [
- "Qwen2ForCausalLM"
- ],
- "attention_dropout": 0.0,
- "bos_token_id": 151643,
- "eos_token_id": 151643,
- "hidden_act": "silu",
- "hidden_size": 5120,
- "initializer_range": 0.02,
- "intermediate_size": 27648,
- "max_position_embeddings": 131072,
- "max_window_layers": 64,
- "model_type": "qwen2",
- "num_attention_heads": 40,
- "num_hidden_layers": 64,
- "num_key_value_heads": 8,
- "quantization": {
- "group_size": 64,
- "bits": null,
- "model.embed_tokens": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.0.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.0.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.0.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.0.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.0.self_attn.rope": false,
- "model.layers.0.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.0.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.0.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.0.input_layernorm": false,
- "model.layers.0.post_attention_layernorm": false,
- "model.layers.1.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.1.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.1.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.1.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.1.self_attn.rope": false,
- "model.layers.1.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.1.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.1.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.1.input_layernorm": false,
- "model.layers.1.post_attention_layernorm": false,
- "model.layers.2.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.2.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.2.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.2.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.2.self_attn.rope": false,
- "model.layers.2.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.2.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.2.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.2.input_layernorm": false,
- "model.layers.2.post_attention_layernorm": false,
- "model.layers.3.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.3.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.3.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.3.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.3.self_attn.rope": false,
- "model.layers.3.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.3.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.3.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.3.input_layernorm": false,
- "model.layers.3.post_attention_layernorm": false,
- "model.layers.4.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.4.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.4.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.4.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.4.self_attn.rope": false,
- "model.layers.4.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.4.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.4.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.4.input_layernorm": false,
- "model.layers.4.post_attention_layernorm": false,
- "model.layers.5.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.5.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.5.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.5.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.5.self_attn.rope": false,
- "model.layers.5.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.5.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.5.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.5.input_layernorm": false,
- "model.layers.5.post_attention_layernorm": false,
- "model.layers.6.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.6.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.6.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.6.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.6.self_attn.rope": false,
- "model.layers.6.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.6.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.6.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.6.input_layernorm": false,
- "model.layers.6.post_attention_layernorm": false,
- "model.layers.7.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.7.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.7.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.7.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.7.self_attn.rope": false,
- "model.layers.7.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.7.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.7.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.7.input_layernorm": false,
- "model.layers.7.post_attention_layernorm": false,
- "model.layers.8.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.self_attn.rope": false,
- "model.layers.8.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.input_layernorm": false,
- "model.layers.8.post_attention_layernorm": false,
- "model.layers.9.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.self_attn.rope": false,
- "model.layers.9.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.input_layernorm": false,
- "model.layers.9.post_attention_layernorm": false,
- "model.layers.10.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.10.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.10.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.10.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.10.self_attn.rope": false,
- "model.layers.10.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.10.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.10.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.10.input_layernorm": false,
- "model.layers.10.post_attention_layernorm": false,
- "model.layers.11.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.self_attn.rope": false,
- "model.layers.11.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.input_layernorm": false,
- "model.layers.11.post_attention_layernorm": false,
- "model.layers.12.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.self_attn.rope": false,
- "model.layers.12.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.input_layernorm": false,
- "model.layers.12.post_attention_layernorm": false,
- "model.layers.13.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.13.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.13.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.13.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.13.self_attn.rope": false,
- "model.layers.13.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.13.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.13.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.13.input_layernorm": false,
- "model.layers.13.post_attention_layernorm": false,
- "model.layers.14.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.self_attn.rope": false,
- "model.layers.14.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.input_layernorm": false,
- "model.layers.14.post_attention_layernorm": false,
- "model.layers.15.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.self_attn.rope": false,
- "model.layers.15.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.input_layernorm": false,
- "model.layers.15.post_attention_layernorm": false,
- "model.layers.16.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.16.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.16.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.16.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.16.self_attn.rope": false,
- "model.layers.16.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.16.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.16.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.16.input_layernorm": false,
- "model.layers.16.post_attention_layernorm": false,
- "model.layers.17.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.self_attn.rope": false,
- "model.layers.17.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.input_layernorm": false,
- "model.layers.17.post_attention_layernorm": false,
- "model.layers.18.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.self_attn.rope": false,
- "model.layers.18.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.input_layernorm": false,
- "model.layers.18.post_attention_layernorm": false,
- "model.layers.19.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.19.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.19.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.19.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.19.self_attn.rope": false,
- "model.layers.19.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.19.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.19.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.19.input_layernorm": false,
- "model.layers.19.post_attention_layernorm": false,
- "model.layers.20.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.self_attn.rope": false,
- "model.layers.20.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.input_layernorm": false,
- "model.layers.20.post_attention_layernorm": false,
- "model.layers.21.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.self_attn.rope": false,
- "model.layers.21.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.input_layernorm": false,
- "model.layers.21.post_attention_layernorm": false,
- "model.layers.22.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.22.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.22.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.22.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.22.self_attn.rope": false,
- "model.layers.22.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.22.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.22.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.22.input_layernorm": false,
- "model.layers.22.post_attention_layernorm": false,
- "model.layers.23.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.self_attn.rope": false,
- "model.layers.23.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.input_layernorm": false,
- "model.layers.23.post_attention_layernorm": false,
- "model.layers.24.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.self_attn.rope": false,
- "model.layers.24.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.input_layernorm": false,
- "model.layers.24.post_attention_layernorm": false,
- "model.layers.25.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.25.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.25.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.25.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.25.self_attn.rope": false,
- "model.layers.25.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.25.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.25.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.25.input_layernorm": false,
- "model.layers.25.post_attention_layernorm": false,
- "model.layers.26.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.self_attn.rope": false,
- "model.layers.26.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.input_layernorm": false,
- "model.layers.26.post_attention_layernorm": false,
- "model.layers.27.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.self_attn.rope": false,
- "model.layers.27.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.input_layernorm": false,
- "model.layers.27.post_attention_layernorm": false,
- "model.layers.28.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.28.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.28.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.28.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.28.self_attn.rope": false,
- "model.layers.28.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.28.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.28.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.28.input_layernorm": false,
- "model.layers.28.post_attention_layernorm": false,
- "model.layers.29.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.self_attn.rope": false,
- "model.layers.29.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.input_layernorm": false,
- "model.layers.29.post_attention_layernorm": false,
- "model.layers.30.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.self_attn.rope": false,
- "model.layers.30.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.input_layernorm": false,
- "model.layers.30.post_attention_layernorm": false,
- "model.layers.31.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.31.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.31.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.31.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.31.self_attn.rope": false,
- "model.layers.31.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.31.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.31.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.31.input_layernorm": false,
- "model.layers.31.post_attention_layernorm": false,
- "model.layers.32.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.self_attn.rope": false,
- "model.layers.32.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.input_layernorm": false,
- "model.layers.32.post_attention_layernorm": false,
- "model.layers.33.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.self_attn.rope": false,
- "model.layers.33.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.input_layernorm": false,
- "model.layers.33.post_attention_layernorm": false,
- "model.layers.34.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.34.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.34.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.34.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.34.self_attn.rope": false,
- "model.layers.34.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.34.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.34.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.34.input_layernorm": false,
- "model.layers.34.post_attention_layernorm": false,
- "model.layers.35.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.self_attn.rope": false,
- "model.layers.35.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.input_layernorm": false,
- "model.layers.35.post_attention_layernorm": false,
- "model.layers.36.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.self_attn.rope": false,
- "model.layers.36.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.input_layernorm": false,
- "model.layers.36.post_attention_layernorm": false,
- "model.layers.37.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.37.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.37.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.37.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.37.self_attn.rope": false,
- "model.layers.37.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.37.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.37.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.37.input_layernorm": false,
- "model.layers.37.post_attention_layernorm": false,
- "model.layers.38.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.self_attn.rope": false,
- "model.layers.38.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.input_layernorm": false,
- "model.layers.38.post_attention_layernorm": false,
- "model.layers.39.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.self_attn.rope": false,
- "model.layers.39.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.input_layernorm": false,
- "model.layers.39.post_attention_layernorm": false,
- "model.layers.40.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.40.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.40.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.40.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.40.self_attn.rope": false,
- "model.layers.40.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.40.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.40.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.40.input_layernorm": false,
- "model.layers.40.post_attention_layernorm": false,
- "model.layers.41.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.self_attn.rope": false,
- "model.layers.41.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.input_layernorm": false,
- "model.layers.41.post_attention_layernorm": false,
- "model.layers.42.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.self_attn.rope": false,
- "model.layers.42.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.input_layernorm": false,
- "model.layers.42.post_attention_layernorm": false,
- "model.layers.43.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.43.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.43.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.43.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.43.self_attn.rope": false,
- "model.layers.43.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.43.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.43.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.43.input_layernorm": false,
- "model.layers.43.post_attention_layernorm": false,
- "model.layers.44.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.self_attn.rope": false,
- "model.layers.44.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.input_layernorm": false,
- "model.layers.44.post_attention_layernorm": false,
- "model.layers.45.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.self_attn.rope": false,
- "model.layers.45.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.input_layernorm": false,
- "model.layers.45.post_attention_layernorm": false,
- "model.layers.46.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.46.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.46.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.46.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.46.self_attn.rope": false,
- "model.layers.46.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.46.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.46.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.46.input_layernorm": false,
- "model.layers.46.post_attention_layernorm": false,
- "model.layers.47.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.self_attn.rope": false,
- "model.layers.47.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.input_layernorm": false,
- "model.layers.47.post_attention_layernorm": false,
- "model.layers.48.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.self_attn.rope": false,
- "model.layers.48.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.input_layernorm": false,
- "model.layers.48.post_attention_layernorm": false,
- "model.layers.49.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.49.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.49.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.49.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.49.self_attn.rope": false,
- "model.layers.49.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.49.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.49.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.49.input_layernorm": false,
- "model.layers.49.post_attention_layernorm": false,
- "model.layers.50.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.self_attn.rope": false,
- "model.layers.50.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.input_layernorm": false,
- "model.layers.50.post_attention_layernorm": false,
- "model.layers.51.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.self_attn.rope": false,
- "model.layers.51.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.input_layernorm": false,
- "model.layers.51.post_attention_layernorm": false,
- "model.layers.52.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.52.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.52.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.52.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.52.self_attn.rope": false,
- "model.layers.52.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.52.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.52.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.52.input_layernorm": false,
- "model.layers.52.post_attention_layernorm": false,
- "model.layers.53.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.self_attn.rope": false,
- "model.layers.53.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.input_layernorm": false,
- "model.layers.53.post_attention_layernorm": false,
- "model.layers.54.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.self_attn.rope": false,
- "model.layers.54.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.input_layernorm": false,
- "model.layers.54.post_attention_layernorm": false,
- "model.layers.55.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.55.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.55.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.55.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.55.self_attn.rope": false,
- "model.layers.55.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.55.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.55.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.55.input_layernorm": false,
- "model.layers.55.post_attention_layernorm": false,
- "model.layers.56.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.56.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.56.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.56.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.56.self_attn.rope": false,
- "model.layers.56.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.56.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.56.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.56.input_layernorm": false,
- "model.layers.56.post_attention_layernorm": false,
- "model.layers.57.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.57.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.57.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.57.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.57.self_attn.rope": false,
- "model.layers.57.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.57.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.57.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.57.input_layernorm": false,
- "model.layers.57.post_attention_layernorm": false,
- "model.layers.58.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.58.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.58.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.58.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.58.self_attn.rope": false,
- "model.layers.58.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.58.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.58.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.58.input_layernorm": false,
- "model.layers.58.post_attention_layernorm": false,
- "model.layers.59.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.59.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.59.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.59.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.59.self_attn.rope": false,
- "model.layers.59.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.59.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.59.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.59.input_layernorm": false,
- "model.layers.59.post_attention_layernorm": false,
- "model.layers.60.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.60.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.60.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.60.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.60.self_attn.rope": false,
- "model.layers.60.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.60.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.60.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.60.input_layernorm": false,
- "model.layers.60.post_attention_layernorm": false,
- "model.layers.61.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.61.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.61.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.61.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.61.self_attn.rope": false,
- "model.layers.61.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.61.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.61.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.61.input_layernorm": false,
- "model.layers.61.post_attention_layernorm": false,
- "model.layers.62.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.62.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.62.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.62.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.62.self_attn.rope": false,
- "model.layers.62.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.62.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.62.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.62.input_layernorm": false,
- "model.layers.62.post_attention_layernorm": false,
- "model.layers.63.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.63.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.63.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.63.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.63.self_attn.rope": false,
- "model.layers.63.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.63.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.63.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.63.input_layernorm": false,
- "model.layers.63.post_attention_layernorm": false,
- "model.norm": false,
- "lm_head": {
- "group_size": 64,
- "bits": 4
- }
- },
- "quantization_config": {
- "group_size": 64,
- "bits": null,
- "model.embed_tokens": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.0.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.0.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.0.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.0.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.0.self_attn.rope": false,
- "model.layers.0.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.0.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.0.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.0.input_layernorm": false,
- "model.layers.0.post_attention_layernorm": false,
- "model.layers.1.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.1.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.1.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.1.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.1.self_attn.rope": false,
- "model.layers.1.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.1.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.1.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.1.input_layernorm": false,
- "model.layers.1.post_attention_layernorm": false,
- "model.layers.2.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.2.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.2.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.2.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.2.self_attn.rope": false,
- "model.layers.2.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.2.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.2.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.2.input_layernorm": false,
- "model.layers.2.post_attention_layernorm": false,
- "model.layers.3.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.3.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.3.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.3.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.3.self_attn.rope": false,
- "model.layers.3.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.3.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.3.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.3.input_layernorm": false,
- "model.layers.3.post_attention_layernorm": false,
- "model.layers.4.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.4.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.4.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.4.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.4.self_attn.rope": false,
- "model.layers.4.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.4.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.4.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.4.input_layernorm": false,
- "model.layers.4.post_attention_layernorm": false,
- "model.layers.5.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.5.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.5.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.5.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.5.self_attn.rope": false,
- "model.layers.5.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.5.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.5.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.5.input_layernorm": false,
- "model.layers.5.post_attention_layernorm": false,
- "model.layers.6.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.6.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.6.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.6.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.6.self_attn.rope": false,
- "model.layers.6.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.6.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.6.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.6.input_layernorm": false,
- "model.layers.6.post_attention_layernorm": false,
- "model.layers.7.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.7.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.7.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.7.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.7.self_attn.rope": false,
- "model.layers.7.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.7.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.7.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.7.input_layernorm": false,
- "model.layers.7.post_attention_layernorm": false,
- "model.layers.8.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.self_attn.rope": false,
- "model.layers.8.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.input_layernorm": false,
- "model.layers.8.post_attention_layernorm": false,
- "model.layers.9.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.self_attn.rope": false,
- "model.layers.9.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.input_layernorm": false,
- "model.layers.9.post_attention_layernorm": false,
- "model.layers.10.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.10.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.10.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.10.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.10.self_attn.rope": false,
- "model.layers.10.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.10.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.10.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.10.input_layernorm": false,
- "model.layers.10.post_attention_layernorm": false,
- "model.layers.11.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.self_attn.rope": false,
- "model.layers.11.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.input_layernorm": false,
- "model.layers.11.post_attention_layernorm": false,
- "model.layers.12.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.self_attn.rope": false,
- "model.layers.12.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.input_layernorm": false,
- "model.layers.12.post_attention_layernorm": false,
- "model.layers.13.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.13.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.13.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.13.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.13.self_attn.rope": false,
- "model.layers.13.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.13.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.13.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.13.input_layernorm": false,
- "model.layers.13.post_attention_layernorm": false,
- "model.layers.14.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.self_attn.rope": false,
- "model.layers.14.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.input_layernorm": false,
- "model.layers.14.post_attention_layernorm": false,
- "model.layers.15.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.self_attn.rope": false,
- "model.layers.15.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.input_layernorm": false,
- "model.layers.15.post_attention_layernorm": false,
- "model.layers.16.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.16.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.16.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.16.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.16.self_attn.rope": false,
- "model.layers.16.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.16.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.16.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.16.input_layernorm": false,
- "model.layers.16.post_attention_layernorm": false,
- "model.layers.17.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.self_attn.rope": false,
- "model.layers.17.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.input_layernorm": false,
- "model.layers.17.post_attention_layernorm": false,
- "model.layers.18.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.self_attn.rope": false,
- "model.layers.18.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.input_layernorm": false,
- "model.layers.18.post_attention_layernorm": false,
- "model.layers.19.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.19.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.19.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.19.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.19.self_attn.rope": false,
- "model.layers.19.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.19.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.19.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.19.input_layernorm": false,
- "model.layers.19.post_attention_layernorm": false,
- "model.layers.20.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.self_attn.rope": false,
- "model.layers.20.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.input_layernorm": false,
- "model.layers.20.post_attention_layernorm": false,
- "model.layers.21.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.self_attn.rope": false,
- "model.layers.21.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.input_layernorm": false,
- "model.layers.21.post_attention_layernorm": false,
- "model.layers.22.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.22.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.22.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.22.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.22.self_attn.rope": false,
- "model.layers.22.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.22.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.22.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.22.input_layernorm": false,
- "model.layers.22.post_attention_layernorm": false,
- "model.layers.23.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.self_attn.rope": false,
- "model.layers.23.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.input_layernorm": false,
- "model.layers.23.post_attention_layernorm": false,
- "model.layers.24.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.self_attn.rope": false,
- "model.layers.24.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.input_layernorm": false,
- "model.layers.24.post_attention_layernorm": false,
- "model.layers.25.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.25.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.25.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.25.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.25.self_attn.rope": false,
- "model.layers.25.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.25.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.25.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.25.input_layernorm": false,
- "model.layers.25.post_attention_layernorm": false,
- "model.layers.26.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.self_attn.rope": false,
- "model.layers.26.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.input_layernorm": false,
- "model.layers.26.post_attention_layernorm": false,
- "model.layers.27.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.self_attn.rope": false,
- "model.layers.27.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.input_layernorm": false,
- "model.layers.27.post_attention_layernorm": false,
- "model.layers.28.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.28.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.28.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.28.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.28.self_attn.rope": false,
- "model.layers.28.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.28.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.28.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.28.input_layernorm": false,
- "model.layers.28.post_attention_layernorm": false,
- "model.layers.29.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.self_attn.rope": false,
- "model.layers.29.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.input_layernorm": false,
- "model.layers.29.post_attention_layernorm": false,
- "model.layers.30.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.self_attn.rope": false,
- "model.layers.30.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.input_layernorm": false,
- "model.layers.30.post_attention_layernorm": false,
- "model.layers.31.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.31.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.31.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.31.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.31.self_attn.rope": false,
- "model.layers.31.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.31.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.31.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.31.input_layernorm": false,
- "model.layers.31.post_attention_layernorm": false,
- "model.layers.32.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.self_attn.rope": false,
- "model.layers.32.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.input_layernorm": false,
- "model.layers.32.post_attention_layernorm": false,
- "model.layers.33.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.self_attn.rope": false,
- "model.layers.33.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.input_layernorm": false,
- "model.layers.33.post_attention_layernorm": false,
- "model.layers.34.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.34.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.34.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.34.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.34.self_attn.rope": false,
- "model.layers.34.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.34.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.34.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.34.input_layernorm": false,
- "model.layers.34.post_attention_layernorm": false,
- "model.layers.35.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.self_attn.rope": false,
- "model.layers.35.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.input_layernorm": false,
- "model.layers.35.post_attention_layernorm": false,
- "model.layers.36.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.self_attn.rope": false,
- "model.layers.36.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.input_layernorm": false,
- "model.layers.36.post_attention_layernorm": false,
- "model.layers.37.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.37.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.37.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.37.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.37.self_attn.rope": false,
- "model.layers.37.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.37.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.37.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.37.input_layernorm": false,
- "model.layers.37.post_attention_layernorm": false,
- "model.layers.38.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.self_attn.rope": false,
- "model.layers.38.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.input_layernorm": false,
- "model.layers.38.post_attention_layernorm": false,
- "model.layers.39.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.self_attn.rope": false,
- "model.layers.39.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.input_layernorm": false,
- "model.layers.39.post_attention_layernorm": false,
- "model.layers.40.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.40.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.40.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.40.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.40.self_attn.rope": false,
- "model.layers.40.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.40.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.40.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.40.input_layernorm": false,
- "model.layers.40.post_attention_layernorm": false,
- "model.layers.41.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.self_attn.rope": false,
- "model.layers.41.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.input_layernorm": false,
- "model.layers.41.post_attention_layernorm": false,
- "model.layers.42.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.self_attn.rope": false,
- "model.layers.42.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.input_layernorm": false,
- "model.layers.42.post_attention_layernorm": false,
- "model.layers.43.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.43.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.43.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.43.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.43.self_attn.rope": false,
- "model.layers.43.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.43.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.43.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.43.input_layernorm": false,
- "model.layers.43.post_attention_layernorm": false,
- "model.layers.44.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.self_attn.rope": false,
- "model.layers.44.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.input_layernorm": false,
- "model.layers.44.post_attention_layernorm": false,
- "model.layers.45.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.self_attn.rope": false,
- "model.layers.45.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.input_layernorm": false,
- "model.layers.45.post_attention_layernorm": false,
- "model.layers.46.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.46.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.46.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.46.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.46.self_attn.rope": false,
- "model.layers.46.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.46.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.46.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.46.input_layernorm": false,
- "model.layers.46.post_attention_layernorm": false,
- "model.layers.47.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.self_attn.rope": false,
- "model.layers.47.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.input_layernorm": false,
- "model.layers.47.post_attention_layernorm": false,
- "model.layers.48.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.self_attn.rope": false,
- "model.layers.48.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.input_layernorm": false,
- "model.layers.48.post_attention_layernorm": false,
- "model.layers.49.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.49.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.49.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.49.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.49.self_attn.rope": false,
- "model.layers.49.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.49.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.49.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.49.input_layernorm": false,
- "model.layers.49.post_attention_layernorm": false,
- "model.layers.50.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.self_attn.rope": false,
- "model.layers.50.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.input_layernorm": false,
- "model.layers.50.post_attention_layernorm": false,
- "model.layers.51.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.self_attn.rope": false,
- "model.layers.51.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.input_layernorm": false,
- "model.layers.51.post_attention_layernorm": false,
- "model.layers.52.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.52.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.52.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.52.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.52.self_attn.rope": false,
- "model.layers.52.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.52.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.52.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.52.input_layernorm": false,
- "model.layers.52.post_attention_layernorm": false,
- "model.layers.53.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.self_attn.rope": false,
- "model.layers.53.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.input_layernorm": false,
- "model.layers.53.post_attention_layernorm": false,
- "model.layers.54.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.self_attn.rope": false,
- "model.layers.54.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.input_layernorm": false,
- "model.layers.54.post_attention_layernorm": false,
- "model.layers.55.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.55.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.55.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.55.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.55.self_attn.rope": false,
- "model.layers.55.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.55.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.55.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.55.input_layernorm": false,
- "model.layers.55.post_attention_layernorm": false,
- "model.layers.56.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.56.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.56.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.56.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.56.self_attn.rope": false,
- "model.layers.56.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.56.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.56.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.56.input_layernorm": false,
- "model.layers.56.post_attention_layernorm": false,
- "model.layers.57.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.57.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.57.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.57.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.57.self_attn.rope": false,
- "model.layers.57.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.57.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.57.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.57.input_layernorm": false,
- "model.layers.57.post_attention_layernorm": false,
- "model.layers.58.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.58.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.58.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.58.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.58.self_attn.rope": false,
- "model.layers.58.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.58.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.58.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.58.input_layernorm": false,
- "model.layers.58.post_attention_layernorm": false,
- "model.layers.59.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.59.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.59.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.59.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.59.self_attn.rope": false,
- "model.layers.59.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.59.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.59.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.59.input_layernorm": false,
- "model.layers.59.post_attention_layernorm": false,
- "model.layers.60.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.60.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.60.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.60.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.60.self_attn.rope": false,
- "model.layers.60.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.60.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.60.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.60.input_layernorm": false,
- "model.layers.60.post_attention_layernorm": false,
- "model.layers.61.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.61.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.61.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.61.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.61.self_attn.rope": false,
- "model.layers.61.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.61.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.61.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.61.input_layernorm": false,
- "model.layers.61.post_attention_layernorm": false,
- "model.layers.62.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.62.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.62.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.62.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.62.self_attn.rope": false,
- "model.layers.62.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.62.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.62.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.62.input_layernorm": false,
- "model.layers.62.post_attention_layernorm": false,
- "model.layers.63.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.63.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.63.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.63.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.63.self_attn.rope": false,
- "model.layers.63.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.63.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.63.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.63.input_layernorm": false,
- "model.layers.63.post_attention_layernorm": false,
- "model.norm": false,
- "lm_head": {
- "group_size": 64,
- "bits": 4
- }
- },
- "rms_norm_eps": 1e-05,
- "rope_theta": 1000000.0,
- "sliding_window": 131072,
- "tie_word_embeddings": false,
- "torch_dtype": "bfloat16",
- "transformers_version": "4.43.1",
- "use_cache": true,
- "use_sliding_window": false,
- "vocab_size": 152064
-}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00001-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00001-of-00003.safetensors
deleted file mode 100644
index 5e4a46446cb401286042a48927c3e6d3a8bd8c2a..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00001-of-00003.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1de09b845c5a77c62056128589fa4686507ffb5edda714fe312c24b90edf8648
-size 5344816524
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00002-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00002-of-00003.safetensors
deleted file mode 100644
index 3d504b72a810f59628f1d1637fd9480c38887bba..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00002-of-00003.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:86ca2f630b5ee185bd684c721deba18e2728d6939953bd4c7c966af6535ade91
-size 5347005848
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00003-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00003-of-00003.safetensors
deleted file mode 100644
index 03be3f611cefb2ba8b78bce74c8aed0e2e12b420..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00003-of-00003.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b86b6d4e4db81b48b23f54745d66f94c1878e08d356aaae40aae0ba69f7b48c8
-size 4328835017
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model.safetensors.index.json
deleted file mode 100644
index 5894d691559fe9b7406f347a18b89b0b273d9aa7..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model.safetensors.index.json
+++ /dev/null
@@ -1,1678 +0,0 @@
-{
- "metadata": {
- "total_size": 15020468224
- },
- "weight_map": {
- "lm_head.biases": "model-00003-of-00003.safetensors",
- "lm_head.scales": "model-00003-of-00003.safetensors",
- "lm_head.weight": "model-00003-of-00003.safetensors",
- "model.embed_tokens.biases": "model-00001-of-00003.safetensors",
- "model.embed_tokens.scales": "model-00001-of-00003.safetensors",
- "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.22.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.22.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.22.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.22.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.23.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.23.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.23.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.23.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.23.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.40.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.46.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.46.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.46.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.46.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.47.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.47.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.47.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.47.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.47.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.47.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.47.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.47.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.47.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.47.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.48.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.48.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.48.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.48.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.48.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.48.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.48.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.48.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.48.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.48.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.48.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.50.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.50.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.60.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.60.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.norm.weight": "model-00003-of-00003.safetensors"
- }
-}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/config.json b/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/config.json
deleted file mode 100644
index c25d6bc33782d800fdf5ada7960ebe5c9a778dd5..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/config.json
+++ /dev/null
@@ -1,4021 +0,0 @@
-{
- "architectures": [
- "Qwen2ForCausalLM"
- ],
- "attention_dropout": 0.0,
- "bos_token_id": 151643,
- "eos_token_id": 151643,
- "hidden_act": "silu",
- "hidden_size": 5120,
- "initializer_range": 0.02,
- "intermediate_size": 27648,
- "max_position_embeddings": 131072,
- "max_window_layers": 64,
- "model_type": "qwen2",
- "num_attention_heads": 40,
- "num_hidden_layers": 64,
- "num_key_value_heads": 8,
- "quantization": {
- "group_size": 64,
- "bits": null,
- "model.embed_tokens": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.0.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.0.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.0.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.0.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.0.self_attn.rope": false,
- "model.layers.0.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.0.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.0.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.0.input_layernorm": false,
- "model.layers.0.post_attention_layernorm": false,
- "model.layers.1.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.1.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.1.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.1.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.1.self_attn.rope": false,
- "model.layers.1.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.1.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.1.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.1.input_layernorm": false,
- "model.layers.1.post_attention_layernorm": false,
- "model.layers.2.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.2.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.2.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.2.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.2.self_attn.rope": false,
- "model.layers.2.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.2.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.2.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.2.input_layernorm": false,
- "model.layers.2.post_attention_layernorm": false,
- "model.layers.3.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.3.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.3.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.3.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.3.self_attn.rope": false,
- "model.layers.3.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.3.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.3.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.3.input_layernorm": false,
- "model.layers.3.post_attention_layernorm": false,
- "model.layers.4.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.4.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.4.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.4.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.4.self_attn.rope": false,
- "model.layers.4.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.4.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.4.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.4.input_layernorm": false,
- "model.layers.4.post_attention_layernorm": false,
- "model.layers.5.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.5.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.5.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.5.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.5.self_attn.rope": false,
- "model.layers.5.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.5.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.5.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.5.input_layernorm": false,
- "model.layers.5.post_attention_layernorm": false,
- "model.layers.6.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.6.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.6.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.6.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.6.self_attn.rope": false,
- "model.layers.6.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.6.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.6.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.6.input_layernorm": false,
- "model.layers.6.post_attention_layernorm": false,
- "model.layers.7.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.7.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.7.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.7.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.7.self_attn.rope": false,
- "model.layers.7.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.7.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.7.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.7.input_layernorm": false,
- "model.layers.7.post_attention_layernorm": false,
- "model.layers.8.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.self_attn.rope": false,
- "model.layers.8.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.input_layernorm": false,
- "model.layers.8.post_attention_layernorm": false,
- "model.layers.9.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.self_attn.rope": false,
- "model.layers.9.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.input_layernorm": false,
- "model.layers.9.post_attention_layernorm": false,
- "model.layers.10.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.10.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.10.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.10.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.10.self_attn.rope": false,
- "model.layers.10.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.10.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.10.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.10.input_layernorm": false,
- "model.layers.10.post_attention_layernorm": false,
- "model.layers.11.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.self_attn.rope": false,
- "model.layers.11.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.input_layernorm": false,
- "model.layers.11.post_attention_layernorm": false,
- "model.layers.12.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.self_attn.rope": false,
- "model.layers.12.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.input_layernorm": false,
- "model.layers.12.post_attention_layernorm": false,
- "model.layers.13.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.13.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.13.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.13.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.13.self_attn.rope": false,
- "model.layers.13.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.13.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.13.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.13.input_layernorm": false,
- "model.layers.13.post_attention_layernorm": false,
- "model.layers.14.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.self_attn.rope": false,
- "model.layers.14.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.input_layernorm": false,
- "model.layers.14.post_attention_layernorm": false,
- "model.layers.15.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.self_attn.rope": false,
- "model.layers.15.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.input_layernorm": false,
- "model.layers.15.post_attention_layernorm": false,
- "model.layers.16.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.16.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.16.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.16.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.16.self_attn.rope": false,
- "model.layers.16.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.16.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.16.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.16.input_layernorm": false,
- "model.layers.16.post_attention_layernorm": false,
- "model.layers.17.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.self_attn.rope": false,
- "model.layers.17.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.input_layernorm": false,
- "model.layers.17.post_attention_layernorm": false,
- "model.layers.18.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.self_attn.rope": false,
- "model.layers.18.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.input_layernorm": false,
- "model.layers.18.post_attention_layernorm": false,
- "model.layers.19.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.19.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.19.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.19.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.19.self_attn.rope": false,
- "model.layers.19.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.19.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.19.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.19.input_layernorm": false,
- "model.layers.19.post_attention_layernorm": false,
- "model.layers.20.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.self_attn.rope": false,
- "model.layers.20.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.input_layernorm": false,
- "model.layers.20.post_attention_layernorm": false,
- "model.layers.21.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.self_attn.rope": false,
- "model.layers.21.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.input_layernorm": false,
- "model.layers.21.post_attention_layernorm": false,
- "model.layers.22.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.22.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.22.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.22.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.22.self_attn.rope": false,
- "model.layers.22.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.22.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.22.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.22.input_layernorm": false,
- "model.layers.22.post_attention_layernorm": false,
- "model.layers.23.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.self_attn.rope": false,
- "model.layers.23.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.input_layernorm": false,
- "model.layers.23.post_attention_layernorm": false,
- "model.layers.24.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.self_attn.rope": false,
- "model.layers.24.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.input_layernorm": false,
- "model.layers.24.post_attention_layernorm": false,
- "model.layers.25.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.25.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.25.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.25.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.25.self_attn.rope": false,
- "model.layers.25.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.25.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.25.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.25.input_layernorm": false,
- "model.layers.25.post_attention_layernorm": false,
- "model.layers.26.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.self_attn.rope": false,
- "model.layers.26.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.input_layernorm": false,
- "model.layers.26.post_attention_layernorm": false,
- "model.layers.27.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.self_attn.rope": false,
- "model.layers.27.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.input_layernorm": false,
- "model.layers.27.post_attention_layernorm": false,
- "model.layers.28.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.28.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.28.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.28.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.28.self_attn.rope": false,
- "model.layers.28.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.28.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.28.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.28.input_layernorm": false,
- "model.layers.28.post_attention_layernorm": false,
- "model.layers.29.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.self_attn.rope": false,
- "model.layers.29.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.input_layernorm": false,
- "model.layers.29.post_attention_layernorm": false,
- "model.layers.30.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.self_attn.rope": false,
- "model.layers.30.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.input_layernorm": false,
- "model.layers.30.post_attention_layernorm": false,
- "model.layers.31.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.31.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.31.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.31.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.31.self_attn.rope": false,
- "model.layers.31.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.31.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.31.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.31.input_layernorm": false,
- "model.layers.31.post_attention_layernorm": false,
- "model.layers.32.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.self_attn.rope": false,
- "model.layers.32.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.input_layernorm": false,
- "model.layers.32.post_attention_layernorm": false,
- "model.layers.33.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.self_attn.rope": false,
- "model.layers.33.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.input_layernorm": false,
- "model.layers.33.post_attention_layernorm": false,
- "model.layers.34.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.34.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.34.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.34.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.34.self_attn.rope": false,
- "model.layers.34.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.34.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.34.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.34.input_layernorm": false,
- "model.layers.34.post_attention_layernorm": false,
- "model.layers.35.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.self_attn.rope": false,
- "model.layers.35.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.input_layernorm": false,
- "model.layers.35.post_attention_layernorm": false,
- "model.layers.36.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.self_attn.rope": false,
- "model.layers.36.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.input_layernorm": false,
- "model.layers.36.post_attention_layernorm": false,
- "model.layers.37.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.37.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.37.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.37.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.37.self_attn.rope": false,
- "model.layers.37.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.37.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.37.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.37.input_layernorm": false,
- "model.layers.37.post_attention_layernorm": false,
- "model.layers.38.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.self_attn.rope": false,
- "model.layers.38.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.input_layernorm": false,
- "model.layers.38.post_attention_layernorm": false,
- "model.layers.39.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.self_attn.rope": false,
- "model.layers.39.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.input_layernorm": false,
- "model.layers.39.post_attention_layernorm": false,
- "model.layers.40.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.40.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.40.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.40.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.40.self_attn.rope": false,
- "model.layers.40.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.40.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.40.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.40.input_layernorm": false,
- "model.layers.40.post_attention_layernorm": false,
- "model.layers.41.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.self_attn.rope": false,
- "model.layers.41.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.input_layernorm": false,
- "model.layers.41.post_attention_layernorm": false,
- "model.layers.42.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.self_attn.rope": false,
- "model.layers.42.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.input_layernorm": false,
- "model.layers.42.post_attention_layernorm": false,
- "model.layers.43.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.43.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.43.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.43.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.43.self_attn.rope": false,
- "model.layers.43.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.43.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.43.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.43.input_layernorm": false,
- "model.layers.43.post_attention_layernorm": false,
- "model.layers.44.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.self_attn.rope": false,
- "model.layers.44.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.input_layernorm": false,
- "model.layers.44.post_attention_layernorm": false,
- "model.layers.45.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.self_attn.rope": false,
- "model.layers.45.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.input_layernorm": false,
- "model.layers.45.post_attention_layernorm": false,
- "model.layers.46.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.46.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.46.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.46.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.46.self_attn.rope": false,
- "model.layers.46.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.46.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.46.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.46.input_layernorm": false,
- "model.layers.46.post_attention_layernorm": false,
- "model.layers.47.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.self_attn.rope": false,
- "model.layers.47.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.input_layernorm": false,
- "model.layers.47.post_attention_layernorm": false,
- "model.layers.48.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.self_attn.rope": false,
- "model.layers.48.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.input_layernorm": false,
- "model.layers.48.post_attention_layernorm": false,
- "model.layers.49.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.49.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.49.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.49.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.49.self_attn.rope": false,
- "model.layers.49.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.49.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.49.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.49.input_layernorm": false,
- "model.layers.49.post_attention_layernorm": false,
- "model.layers.50.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.self_attn.rope": false,
- "model.layers.50.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.input_layernorm": false,
- "model.layers.50.post_attention_layernorm": false,
- "model.layers.51.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.self_attn.rope": false,
- "model.layers.51.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.input_layernorm": false,
- "model.layers.51.post_attention_layernorm": false,
- "model.layers.52.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.52.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.52.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.52.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.52.self_attn.rope": false,
- "model.layers.52.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.52.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.52.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.52.input_layernorm": false,
- "model.layers.52.post_attention_layernorm": false,
- "model.layers.53.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.self_attn.rope": false,
- "model.layers.53.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.input_layernorm": false,
- "model.layers.53.post_attention_layernorm": false,
- "model.layers.54.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.self_attn.rope": false,
- "model.layers.54.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.input_layernorm": false,
- "model.layers.54.post_attention_layernorm": false,
- "model.layers.55.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.55.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.55.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.55.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.55.self_attn.rope": false,
- "model.layers.55.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.55.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.55.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.55.input_layernorm": false,
- "model.layers.55.post_attention_layernorm": false,
- "model.layers.56.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.56.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.56.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.56.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.56.self_attn.rope": false,
- "model.layers.56.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.56.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.56.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.56.input_layernorm": false,
- "model.layers.56.post_attention_layernorm": false,
- "model.layers.57.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.57.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.57.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.57.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.57.self_attn.rope": false,
- "model.layers.57.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.57.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.57.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.57.input_layernorm": false,
- "model.layers.57.post_attention_layernorm": false,
- "model.layers.58.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.58.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.58.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.58.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.58.self_attn.rope": false,
- "model.layers.58.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.58.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.58.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.58.input_layernorm": false,
- "model.layers.58.post_attention_layernorm": false,
- "model.layers.59.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.59.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.59.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.59.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.59.self_attn.rope": false,
- "model.layers.59.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.59.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.59.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.59.input_layernorm": false,
- "model.layers.59.post_attention_layernorm": false,
- "model.layers.60.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.60.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.60.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.60.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.60.self_attn.rope": false,
- "model.layers.60.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.60.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.60.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.60.input_layernorm": false,
- "model.layers.60.post_attention_layernorm": false,
- "model.layers.61.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.61.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.61.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.61.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.61.self_attn.rope": false,
- "model.layers.61.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.61.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.61.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.61.input_layernorm": false,
- "model.layers.61.post_attention_layernorm": false,
- "model.layers.62.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.62.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.62.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.62.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.62.self_attn.rope": false,
- "model.layers.62.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.62.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.62.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.62.input_layernorm": false,
- "model.layers.62.post_attention_layernorm": false,
- "model.layers.63.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.63.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.63.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.63.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.63.self_attn.rope": false,
- "model.layers.63.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.63.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.63.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.63.input_layernorm": false,
- "model.layers.63.post_attention_layernorm": false,
- "model.norm": false,
- "lm_head": {
- "group_size": 64,
- "bits": 4
- }
- },
- "quantization_config": {
- "group_size": 64,
- "bits": null,
- "model.embed_tokens": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.0.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.0.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.0.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.0.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.0.self_attn.rope": false,
- "model.layers.0.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.0.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.0.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.0.input_layernorm": false,
- "model.layers.0.post_attention_layernorm": false,
- "model.layers.1.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.1.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.1.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.1.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.1.self_attn.rope": false,
- "model.layers.1.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.1.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.1.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.1.input_layernorm": false,
- "model.layers.1.post_attention_layernorm": false,
- "model.layers.2.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.2.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.2.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.2.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.2.self_attn.rope": false,
- "model.layers.2.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.2.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.2.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.2.input_layernorm": false,
- "model.layers.2.post_attention_layernorm": false,
- "model.layers.3.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.3.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.3.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.3.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.3.self_attn.rope": false,
- "model.layers.3.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.3.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.3.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.3.input_layernorm": false,
- "model.layers.3.post_attention_layernorm": false,
- "model.layers.4.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.4.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.4.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.4.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.4.self_attn.rope": false,
- "model.layers.4.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.4.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.4.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.4.input_layernorm": false,
- "model.layers.4.post_attention_layernorm": false,
- "model.layers.5.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.5.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.5.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.5.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.5.self_attn.rope": false,
- "model.layers.5.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.5.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.5.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.5.input_layernorm": false,
- "model.layers.5.post_attention_layernorm": false,
- "model.layers.6.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.6.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.6.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.6.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.6.self_attn.rope": false,
- "model.layers.6.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.6.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.6.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.6.input_layernorm": false,
- "model.layers.6.post_attention_layernorm": false,
- "model.layers.7.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.7.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.7.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.7.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.7.self_attn.rope": false,
- "model.layers.7.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.7.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.7.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.7.input_layernorm": false,
- "model.layers.7.post_attention_layernorm": false,
- "model.layers.8.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.self_attn.rope": false,
- "model.layers.8.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.8.input_layernorm": false,
- "model.layers.8.post_attention_layernorm": false,
- "model.layers.9.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.self_attn.rope": false,
- "model.layers.9.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.9.input_layernorm": false,
- "model.layers.9.post_attention_layernorm": false,
- "model.layers.10.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.10.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.10.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.10.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.10.self_attn.rope": false,
- "model.layers.10.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.10.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.10.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.10.input_layernorm": false,
- "model.layers.10.post_attention_layernorm": false,
- "model.layers.11.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.self_attn.rope": false,
- "model.layers.11.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.11.input_layernorm": false,
- "model.layers.11.post_attention_layernorm": false,
- "model.layers.12.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.self_attn.rope": false,
- "model.layers.12.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.12.input_layernorm": false,
- "model.layers.12.post_attention_layernorm": false,
- "model.layers.13.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.13.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.13.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.13.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.13.self_attn.rope": false,
- "model.layers.13.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.13.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.13.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.13.input_layernorm": false,
- "model.layers.13.post_attention_layernorm": false,
- "model.layers.14.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.self_attn.rope": false,
- "model.layers.14.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.14.input_layernorm": false,
- "model.layers.14.post_attention_layernorm": false,
- "model.layers.15.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.self_attn.rope": false,
- "model.layers.15.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.15.input_layernorm": false,
- "model.layers.15.post_attention_layernorm": false,
- "model.layers.16.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.16.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.16.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.16.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.16.self_attn.rope": false,
- "model.layers.16.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.16.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.16.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.16.input_layernorm": false,
- "model.layers.16.post_attention_layernorm": false,
- "model.layers.17.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.self_attn.rope": false,
- "model.layers.17.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.17.input_layernorm": false,
- "model.layers.17.post_attention_layernorm": false,
- "model.layers.18.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.self_attn.rope": false,
- "model.layers.18.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.18.input_layernorm": false,
- "model.layers.18.post_attention_layernorm": false,
- "model.layers.19.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.19.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.19.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.19.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.19.self_attn.rope": false,
- "model.layers.19.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.19.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.19.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.19.input_layernorm": false,
- "model.layers.19.post_attention_layernorm": false,
- "model.layers.20.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.self_attn.rope": false,
- "model.layers.20.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.20.input_layernorm": false,
- "model.layers.20.post_attention_layernorm": false,
- "model.layers.21.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.self_attn.rope": false,
- "model.layers.21.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.21.input_layernorm": false,
- "model.layers.21.post_attention_layernorm": false,
- "model.layers.22.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.22.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.22.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.22.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.22.self_attn.rope": false,
- "model.layers.22.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.22.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.22.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.22.input_layernorm": false,
- "model.layers.22.post_attention_layernorm": false,
- "model.layers.23.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.self_attn.rope": false,
- "model.layers.23.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.23.input_layernorm": false,
- "model.layers.23.post_attention_layernorm": false,
- "model.layers.24.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.self_attn.rope": false,
- "model.layers.24.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.24.input_layernorm": false,
- "model.layers.24.post_attention_layernorm": false,
- "model.layers.25.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.25.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.25.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.25.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.25.self_attn.rope": false,
- "model.layers.25.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.25.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.25.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.25.input_layernorm": false,
- "model.layers.25.post_attention_layernorm": false,
- "model.layers.26.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.self_attn.rope": false,
- "model.layers.26.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.26.input_layernorm": false,
- "model.layers.26.post_attention_layernorm": false,
- "model.layers.27.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.self_attn.rope": false,
- "model.layers.27.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.27.input_layernorm": false,
- "model.layers.27.post_attention_layernorm": false,
- "model.layers.28.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.28.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.28.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.28.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.28.self_attn.rope": false,
- "model.layers.28.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.28.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.28.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.28.input_layernorm": false,
- "model.layers.28.post_attention_layernorm": false,
- "model.layers.29.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.self_attn.rope": false,
- "model.layers.29.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.29.input_layernorm": false,
- "model.layers.29.post_attention_layernorm": false,
- "model.layers.30.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.self_attn.rope": false,
- "model.layers.30.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.30.input_layernorm": false,
- "model.layers.30.post_attention_layernorm": false,
- "model.layers.31.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.31.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.31.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.31.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.31.self_attn.rope": false,
- "model.layers.31.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.31.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.31.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.31.input_layernorm": false,
- "model.layers.31.post_attention_layernorm": false,
- "model.layers.32.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.self_attn.rope": false,
- "model.layers.32.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.32.input_layernorm": false,
- "model.layers.32.post_attention_layernorm": false,
- "model.layers.33.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.self_attn.rope": false,
- "model.layers.33.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.33.input_layernorm": false,
- "model.layers.33.post_attention_layernorm": false,
- "model.layers.34.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.34.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.34.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.34.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.34.self_attn.rope": false,
- "model.layers.34.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.34.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.34.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.34.input_layernorm": false,
- "model.layers.34.post_attention_layernorm": false,
- "model.layers.35.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.self_attn.rope": false,
- "model.layers.35.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.35.input_layernorm": false,
- "model.layers.35.post_attention_layernorm": false,
- "model.layers.36.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.self_attn.rope": false,
- "model.layers.36.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.36.input_layernorm": false,
- "model.layers.36.post_attention_layernorm": false,
- "model.layers.37.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.37.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.37.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.37.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.37.self_attn.rope": false,
- "model.layers.37.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.37.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.37.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.37.input_layernorm": false,
- "model.layers.37.post_attention_layernorm": false,
- "model.layers.38.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.self_attn.rope": false,
- "model.layers.38.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.38.input_layernorm": false,
- "model.layers.38.post_attention_layernorm": false,
- "model.layers.39.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.self_attn.rope": false,
- "model.layers.39.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.39.input_layernorm": false,
- "model.layers.39.post_attention_layernorm": false,
- "model.layers.40.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.40.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.40.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.40.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.40.self_attn.rope": false,
- "model.layers.40.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.40.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.40.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.40.input_layernorm": false,
- "model.layers.40.post_attention_layernorm": false,
- "model.layers.41.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.self_attn.rope": false,
- "model.layers.41.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.41.input_layernorm": false,
- "model.layers.41.post_attention_layernorm": false,
- "model.layers.42.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.self_attn.rope": false,
- "model.layers.42.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.42.input_layernorm": false,
- "model.layers.42.post_attention_layernorm": false,
- "model.layers.43.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.43.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.43.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.43.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.43.self_attn.rope": false,
- "model.layers.43.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.43.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.43.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.43.input_layernorm": false,
- "model.layers.43.post_attention_layernorm": false,
- "model.layers.44.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.self_attn.rope": false,
- "model.layers.44.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.44.input_layernorm": false,
- "model.layers.44.post_attention_layernorm": false,
- "model.layers.45.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.self_attn.rope": false,
- "model.layers.45.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.45.input_layernorm": false,
- "model.layers.45.post_attention_layernorm": false,
- "model.layers.46.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.46.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.46.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.46.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.46.self_attn.rope": false,
- "model.layers.46.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.46.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.46.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.46.input_layernorm": false,
- "model.layers.46.post_attention_layernorm": false,
- "model.layers.47.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.self_attn.rope": false,
- "model.layers.47.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.47.input_layernorm": false,
- "model.layers.47.post_attention_layernorm": false,
- "model.layers.48.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.self_attn.rope": false,
- "model.layers.48.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.48.input_layernorm": false,
- "model.layers.48.post_attention_layernorm": false,
- "model.layers.49.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.49.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.49.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.49.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.49.self_attn.rope": false,
- "model.layers.49.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.49.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.49.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.49.input_layernorm": false,
- "model.layers.49.post_attention_layernorm": false,
- "model.layers.50.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.self_attn.rope": false,
- "model.layers.50.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.50.input_layernorm": false,
- "model.layers.50.post_attention_layernorm": false,
- "model.layers.51.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.self_attn.rope": false,
- "model.layers.51.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.51.input_layernorm": false,
- "model.layers.51.post_attention_layernorm": false,
- "model.layers.52.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.52.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.52.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.52.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.52.self_attn.rope": false,
- "model.layers.52.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.52.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.52.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.52.input_layernorm": false,
- "model.layers.52.post_attention_layernorm": false,
- "model.layers.53.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.self_attn.rope": false,
- "model.layers.53.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.53.input_layernorm": false,
- "model.layers.53.post_attention_layernorm": false,
- "model.layers.54.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.self_attn.v_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.self_attn.rope": false,
- "model.layers.54.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.mlp.down_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.54.input_layernorm": false,
- "model.layers.54.post_attention_layernorm": false,
- "model.layers.55.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.55.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.55.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.55.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.55.self_attn.rope": false,
- "model.layers.55.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.55.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.55.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.55.input_layernorm": false,
- "model.layers.55.post_attention_layernorm": false,
- "model.layers.56.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.56.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.56.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.56.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.56.self_attn.rope": false,
- "model.layers.56.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.56.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.56.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.56.input_layernorm": false,
- "model.layers.56.post_attention_layernorm": false,
- "model.layers.57.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.57.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.57.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.57.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.57.self_attn.rope": false,
- "model.layers.57.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.57.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.57.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.57.input_layernorm": false,
- "model.layers.57.post_attention_layernorm": false,
- "model.layers.58.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.58.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.58.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.58.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.58.self_attn.rope": false,
- "model.layers.58.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.58.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.58.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.58.input_layernorm": false,
- "model.layers.58.post_attention_layernorm": false,
- "model.layers.59.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.59.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.59.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.59.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.59.self_attn.rope": false,
- "model.layers.59.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.59.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.59.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.59.input_layernorm": false,
- "model.layers.59.post_attention_layernorm": false,
- "model.layers.60.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.60.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.60.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.60.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.60.self_attn.rope": false,
- "model.layers.60.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.60.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.60.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.60.input_layernorm": false,
- "model.layers.60.post_attention_layernorm": false,
- "model.layers.61.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.61.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.61.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.61.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.61.self_attn.rope": false,
- "model.layers.61.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.61.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.61.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.61.input_layernorm": false,
- "model.layers.61.post_attention_layernorm": false,
- "model.layers.62.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.62.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.62.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.62.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.62.self_attn.rope": false,
- "model.layers.62.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.62.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.62.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.62.input_layernorm": false,
- "model.layers.62.post_attention_layernorm": false,
- "model.layers.63.self_attn.q_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.63.self_attn.k_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.63.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.63.self_attn.o_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.63.self_attn.rope": false,
- "model.layers.63.mlp.gate_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.63.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.63.mlp.up_proj": {
- "group_size": 64,
- "bits": 3
- },
- "model.layers.63.input_layernorm": false,
- "model.layers.63.post_attention_layernorm": false,
- "model.norm": false,
- "lm_head": {
- "group_size": 64,
- "bits": 4
- }
- },
- "rms_norm_eps": 1e-05,
- "rope_theta": 1000000.0,
- "sliding_window": 131072,
- "tie_word_embeddings": false,
- "torch_dtype": "bfloat16",
- "transformers_version": "4.43.1",
- "use_cache": true,
- "use_sliding_window": false,
- "vocab_size": 152064
-}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00001-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00001-of-00003.safetensors
deleted file mode 100644
index 5e4a46446cb401286042a48927c3e6d3a8bd8c2a..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00001-of-00003.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1de09b845c5a77c62056128589fa4686507ffb5edda714fe312c24b90edf8648
-size 5344816524
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00002-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00002-of-00003.safetensors
deleted file mode 100644
index 3d504b72a810f59628f1d1637fd9480c38887bba..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00002-of-00003.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:86ca2f630b5ee185bd684c721deba18e2728d6939953bd4c7c966af6535ade91
-size 5347005848
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00003-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00003-of-00003.safetensors
deleted file mode 100644
index 03be3f611cefb2ba8b78bce74c8aed0e2e12b420..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00003-of-00003.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b86b6d4e4db81b48b23f54745d66f94c1878e08d356aaae40aae0ba69f7b48c8
-size 4328835017
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model.safetensors.index.json
deleted file mode 100644
index 5894d691559fe9b7406f347a18b89b0b273d9aa7..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model.safetensors.index.json
+++ /dev/null
@@ -1,1678 +0,0 @@
-{
- "metadata": {
- "total_size": 15020468224
- },
- "weight_map": {
- "lm_head.biases": "model-00003-of-00003.safetensors",
- "lm_head.scales": "model-00003-of-00003.safetensors",
- "lm_head.weight": "model-00003-of-00003.safetensors",
- "model.embed_tokens.biases": "model-00001-of-00003.safetensors",
- "model.embed_tokens.scales": "model-00001-of-00003.safetensors",
- "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.22.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.22.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.22.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.22.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.23.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.23.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.23.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.23.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.23.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.40.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.46.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.46.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.46.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.46.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.47.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.47.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.47.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.47.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.47.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.47.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.47.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.47.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.47.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.47.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.48.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.48.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.48.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.48.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.48.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.48.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.48.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.48.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.48.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.48.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.48.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.50.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.50.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.60.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.60.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.norm.weight": "model-00003-of-00003.safetensors"
- }
-}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3bit/config.json b/DeepSeek-R1-Distill-Qwen-32B-3bit/config.json
deleted file mode 100644
index 7d7ebe2eb98861da258a639106462a672a45dc19..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-3bit/config.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
- "architectures": [
- "Qwen2ForCausalLM"
- ],
- "attention_dropout": 0.0,
- "bos_token_id": 151643,
- "eos_token_id": 151643,
- "hidden_act": "silu",
- "hidden_size": 5120,
- "initializer_range": 0.02,
- "intermediate_size": 27648,
- "max_position_embeddings": 131072,
- "max_window_layers": 64,
- "model_type": "qwen2",
- "num_attention_heads": 40,
- "num_hidden_layers": 64,
- "num_key_value_heads": 8,
- "quantization": {
- "group_size": 64,
- "bits": 3
- },
- "quantization_config": {
- "group_size": 64,
- "bits": 3
- },
- "rms_norm_eps": 1e-05,
- "rope_theta": 1000000.0,
- "sliding_window": 131072,
- "tie_word_embeddings": false,
- "torch_dtype": "bfloat16",
- "transformers_version": "4.43.1",
- "use_cache": true,
- "use_sliding_window": false,
- "vocab_size": 152064
-}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3bit/model-00001-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B-3bit/model-00001-of-00003.safetensors
deleted file mode 100644
index 55a719b6fb705f3879d168a1169b7bede9b45a75..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-3bit/model-00001-of-00003.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:df28fc49354643e4296ed66bccf6526153a646ad35a9419981d0910ab6bbc135
-size 5337317621
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3bit/model-00002-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B-3bit/model-00002-of-00003.safetensors
deleted file mode 100644
index fec208e035af0faf2a3597b17dc4e0c7c48f32df..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-3bit/model-00002-of-00003.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ec2df739f0f8748043700a3654acd764a9e0e613d7a8927a80ee39d1a08cef24
-size 5333936095
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3bit/model-00003-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B-3bit/model-00003-of-00003.safetensors
deleted file mode 100644
index ec71156413e33dfc3e1e31e7eb09e3015d8c0100..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-3bit/model-00003-of-00003.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:163ab92116e3a30ff1196343de0559f39f90211cb8e0b30a78727cc57d712597
-size 3664880049
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3bit/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B-3bit/model.safetensors.index.json
deleted file mode 100644
index 0ecaad16f85e981118dfea7127056660adf05a44..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-3bit/model.safetensors.index.json
+++ /dev/null
@@ -1,1678 +0,0 @@
-{
- "metadata": {
- "total_size": 14335944704
- },
- "weight_map": {
- "lm_head.biases": "model-00003-of-00003.safetensors",
- "lm_head.scales": "model-00003-of-00003.safetensors",
- "lm_head.weight": "model-00003-of-00003.safetensors",
- "model.embed_tokens.biases": "model-00001-of-00003.safetensors",
- "model.embed_tokens.scales": "model-00001-of-00003.safetensors",
- "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.22.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.22.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.22.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.22.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.23.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.23.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.23.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.23.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.23.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.40.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.47.input_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.47.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.47.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.47.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.47.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.47.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.47.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.47.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.47.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.47.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.48.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.48.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.48.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.48.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.48.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.48.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.48.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.48.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.48.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.48.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.48.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.48.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
- "model.layers.48.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
- "model.layers.49.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.49.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.49.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.50.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.50.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.50.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.50.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.51.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.51.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.52.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.52.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.53.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.53.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.54.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.54.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.55.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.55.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.56.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.56.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.57.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.57.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.58.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.58.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.59.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.59.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.60.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.60.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.60.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.60.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.61.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.61.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.62.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.input_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
- "model.layers.63.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
- "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
- "model.norm.weight": "model-00003-of-00003.safetensors"
- }
-}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3bit/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B-3bit/special_tokens_map.json
deleted file mode 100644
index 1d385d62cf08bca35254547902b792c243656ec1..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-3bit/special_tokens_map.json
+++ /dev/null
@@ -1,23 +0,0 @@
-{
- "bos_token": {
- "content": "<｜begin▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- },
- "eos_token": {
- "content": "<｜end▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- },
- "pad_token": {
- "content": "<｜end▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- }
-}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3bit/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B-3bit/tokenizer.json
deleted file mode 100644
index 1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-3bit/tokenizer.json
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
-size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3bit/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B-3bit/tokenizer_config.json
deleted file mode 100644
index ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-3bit/tokenizer_config.json
+++ /dev/null
@@ -1,195 +0,0 @@
-{
- "add_bos_token": true,
- "add_eos_token": false,
- "add_prefix_space": null,
- "added_tokens_decoder": {
- "151643": {
- "content": "<｜end▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151644": {
- "content": "<｜User｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151645": {
- "content": "<｜Assistant｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151646": {
- "content": "<｜begin▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151647": {
- "content": "<|EOT|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151648": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151649": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151650": {
- "content": "<|quad_start|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151651": {
- "content": "<|quad_end|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151652": {
- "content": "<|vision_start|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151653": {
- "content": "<|vision_end|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151654": {
- "content": "<|vision_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151655": {
- "content": "<|image_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151656": {
- "content": "<|video_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151657": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151658": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151659": {
- "content": "<|fim_prefix|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151660": {
- "content": "<|fim_middle|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151661": {
- "content": "<|fim_suffix|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151662": {
- "content": "<|fim_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151663": {
- "content": "<|repo_name|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151664": {
- "content": "<|file_sep|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- }
- },
- "bos_token": "<｜begin▁of▁sentence｜>",
- "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
- "clean_up_tokenization_spaces": false,
- "eos_token": "<｜end▁of▁sentence｜>",
- "extra_special_tokens": {},
- "legacy": true,
- "model_max_length": 16384,
- "pad_token": "<｜end▁of▁sentence｜>",
- "sp_model_kwargs": {},
- "tokenizer_class": "LlamaTokenizerFast",
- "unk_token": null,
- "use_default_system_prompt": false
-}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/special_tokens_map.json
deleted file mode 100644
index 1d385d62cf08bca35254547902b792c243656ec1..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/special_tokens_map.json
+++ /dev/null
@@ -1,23 +0,0 @@
-{
- "bos_token": {
- "content": "<｜begin▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- },
- "eos_token": {
- "content": "<｜end▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- },
- "pad_token": {
- "content": "<｜end▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- }
-}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/tokenizer.json
deleted file mode 100644
index 1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/tokenizer.json
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
-size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/tokenizer_config.json
deleted file mode 100644
index ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/tokenizer_config.json
+++ /dev/null
@@ -1,195 +0,0 @@
-{
- "add_bos_token": true,
- "add_eos_token": false,
- "add_prefix_space": null,
- "added_tokens_decoder": {
- "151643": {
- "content": "<｜end▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151644": {
- "content": "<｜User｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151645": {
- "content": "<｜Assistant｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151646": {
- "content": "<｜begin▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151647": {
- "content": "<|EOT|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151648": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151649": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151650": {
- "content": "<|quad_start|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151651": {
- "content": "<|quad_end|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151652": {
- "content": "<|vision_start|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151653": {
- "content": "<|vision_end|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151654": {
- "content": "<|vision_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151655": {
- "content": "<|image_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151656": {
- "content": "<|video_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151657": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151658": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151659": {
- "content": "<|fim_prefix|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151660": {
- "content": "<|fim_middle|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151661": {
- "content": "<|fim_suffix|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151662": {
- "content": "<|fim_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151663": {
- "content": "<|repo_name|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151664": {
- "content": "<|file_sep|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- }
- },
- "bos_token": "<｜begin▁of▁sentence｜>",
- "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
- "clean_up_tokenization_spaces": false,
- "eos_token": "<｜end▁of▁sentence｜>",
- "extra_special_tokens": {},
- "legacy": true,
- "model_max_length": 16384,
- "pad_token": "<｜end▁of▁sentence｜>",
- "sp_model_kwargs": {},
- "tokenizer_class": "LlamaTokenizerFast",
- "unk_token": null,
- "use_default_system_prompt": false
-}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/config.json b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/config.json
deleted file mode 100644
index ad55fbcc50420194feca55ea5f985a102fa7d648..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/config.json
+++ /dev/null
@@ -1,4021 +0,0 @@
-{
- "architectures": [
- "Qwen2ForCausalLM"
- ],
- "attention_dropout": 0.0,
- "bos_token_id": 151643,
- "eos_token_id": 151643,
- "hidden_act": "silu",
- "hidden_size": 5120,
- "initializer_range": 0.02,
- "intermediate_size": 27648,
- "max_position_embeddings": 131072,
- "max_window_layers": 64,
- "model_type": "qwen2",
- "num_attention_heads": 40,
- "num_hidden_layers": 64,
- "num_key_value_heads": 8,
- "quantization": {
- "group_size": 64,
- "bits": null,
- "model.embed_tokens": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.0.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.0.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.0.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.0.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.0.self_attn.rope": false,
- "model.layers.0.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.0.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.0.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.0.input_layernorm": false,
- "model.layers.0.post_attention_layernorm": false,
- "model.layers.1.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.1.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.1.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.1.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.1.self_attn.rope": false,
- "model.layers.1.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.1.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.1.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.1.input_layernorm": false,
- "model.layers.1.post_attention_layernorm": false,
- "model.layers.2.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.2.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.2.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.2.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.2.self_attn.rope": false,
- "model.layers.2.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.2.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.2.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.2.input_layernorm": false,
- "model.layers.2.post_attention_layernorm": false,
- "model.layers.3.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.3.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.3.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.3.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.3.self_attn.rope": false,
- "model.layers.3.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.3.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.3.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.3.input_layernorm": false,
- "model.layers.3.post_attention_layernorm": false,
- "model.layers.4.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.4.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.4.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.4.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.4.self_attn.rope": false,
- "model.layers.4.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.4.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.4.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.4.input_layernorm": false,
- "model.layers.4.post_attention_layernorm": false,
- "model.layers.5.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.5.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.5.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.5.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.5.self_attn.rope": false,
- "model.layers.5.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.5.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.5.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.5.input_layernorm": false,
- "model.layers.5.post_attention_layernorm": false,
- "model.layers.6.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.6.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.6.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.6.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.6.self_attn.rope": false,
- "model.layers.6.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.6.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.6.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.6.input_layernorm": false,
- "model.layers.6.post_attention_layernorm": false,
- "model.layers.7.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.7.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.7.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.7.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.7.self_attn.rope": false,
- "model.layers.7.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.7.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.7.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.7.input_layernorm": false,
- "model.layers.7.post_attention_layernorm": false,
- "model.layers.8.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.8.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.8.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.8.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.8.self_attn.rope": false,
- "model.layers.8.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.8.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.8.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.8.input_layernorm": false,
- "model.layers.8.post_attention_layernorm": false,
- "model.layers.9.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.9.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.9.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.9.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.9.self_attn.rope": false,
- "model.layers.9.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.9.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.9.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.9.input_layernorm": false,
- "model.layers.9.post_attention_layernorm": false,
- "model.layers.10.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.10.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.10.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.10.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.10.self_attn.rope": false,
- "model.layers.10.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.10.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.10.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.10.input_layernorm": false,
- "model.layers.10.post_attention_layernorm": false,
- "model.layers.11.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.11.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.11.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.11.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.11.self_attn.rope": false,
- "model.layers.11.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.11.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.11.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.11.input_layernorm": false,
- "model.layers.11.post_attention_layernorm": false,
- "model.layers.12.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.12.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.12.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.12.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.12.self_attn.rope": false,
- "model.layers.12.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.12.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.12.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.12.input_layernorm": false,
- "model.layers.12.post_attention_layernorm": false,
- "model.layers.13.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.13.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.13.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.13.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.13.self_attn.rope": false,
- "model.layers.13.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.13.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.13.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.13.input_layernorm": false,
- "model.layers.13.post_attention_layernorm": false,
- "model.layers.14.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.14.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.14.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.14.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.14.self_attn.rope": false,
- "model.layers.14.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.14.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.14.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.14.input_layernorm": false,
- "model.layers.14.post_attention_layernorm": false,
- "model.layers.15.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.15.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.15.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.15.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.15.self_attn.rope": false,
- "model.layers.15.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.15.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.15.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.15.input_layernorm": false,
- "model.layers.15.post_attention_layernorm": false,
- "model.layers.16.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.16.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.16.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.16.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.16.self_attn.rope": false,
- "model.layers.16.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.16.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.16.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.16.input_layernorm": false,
- "model.layers.16.post_attention_layernorm": false,
- "model.layers.17.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.17.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.17.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.17.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.17.self_attn.rope": false,
- "model.layers.17.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.17.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.17.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.17.input_layernorm": false,
- "model.layers.17.post_attention_layernorm": false,
- "model.layers.18.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.18.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.18.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.18.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.18.self_attn.rope": false,
- "model.layers.18.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.18.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.18.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.18.input_layernorm": false,
- "model.layers.18.post_attention_layernorm": false,
- "model.layers.19.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.19.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.19.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.19.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.19.self_attn.rope": false,
- "model.layers.19.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.19.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.19.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.19.input_layernorm": false,
- "model.layers.19.post_attention_layernorm": false,
- "model.layers.20.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.20.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.20.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.20.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.20.self_attn.rope": false,
- "model.layers.20.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.20.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.20.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.20.input_layernorm": false,
- "model.layers.20.post_attention_layernorm": false,
- "model.layers.21.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.21.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.21.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.21.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.21.self_attn.rope": false,
- "model.layers.21.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.21.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.21.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.21.input_layernorm": false,
- "model.layers.21.post_attention_layernorm": false,
- "model.layers.22.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.22.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.22.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.22.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.22.self_attn.rope": false,
- "model.layers.22.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.22.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.22.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.22.input_layernorm": false,
- "model.layers.22.post_attention_layernorm": false,
- "model.layers.23.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.23.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.23.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.23.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.23.self_attn.rope": false,
- "model.layers.23.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.23.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.23.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.23.input_layernorm": false,
- "model.layers.23.post_attention_layernorm": false,
- "model.layers.24.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.24.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.24.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.24.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.24.self_attn.rope": false,
- "model.layers.24.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.24.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.24.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.24.input_layernorm": false,
- "model.layers.24.post_attention_layernorm": false,
- "model.layers.25.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.25.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.25.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.25.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.25.self_attn.rope": false,
- "model.layers.25.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.25.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.25.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.25.input_layernorm": false,
- "model.layers.25.post_attention_layernorm": false,
- "model.layers.26.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.26.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.26.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.26.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.26.self_attn.rope": false,
- "model.layers.26.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.26.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.26.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.26.input_layernorm": false,
- "model.layers.26.post_attention_layernorm": false,
- "model.layers.27.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.27.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.27.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.27.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.27.self_attn.rope": false,
- "model.layers.27.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.27.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.27.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.27.input_layernorm": false,
- "model.layers.27.post_attention_layernorm": false,
- "model.layers.28.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.28.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.28.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.28.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.28.self_attn.rope": false,
- "model.layers.28.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.28.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.28.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.28.input_layernorm": false,
- "model.layers.28.post_attention_layernorm": false,
- "model.layers.29.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.29.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.29.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.29.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.29.self_attn.rope": false,
- "model.layers.29.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.29.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.29.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.29.input_layernorm": false,
- "model.layers.29.post_attention_layernorm": false,
- "model.layers.30.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.30.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.30.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.30.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.30.self_attn.rope": false,
- "model.layers.30.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.30.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.30.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.30.input_layernorm": false,
- "model.layers.30.post_attention_layernorm": false,
- "model.layers.31.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.31.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.31.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.31.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.31.self_attn.rope": false,
- "model.layers.31.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.31.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.31.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.31.input_layernorm": false,
- "model.layers.31.post_attention_layernorm": false,
- "model.layers.32.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.32.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.32.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.32.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.32.self_attn.rope": false,
- "model.layers.32.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.32.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.32.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.32.input_layernorm": false,
- "model.layers.32.post_attention_layernorm": false,
- "model.layers.33.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.33.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.33.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.33.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.33.self_attn.rope": false,
- "model.layers.33.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.33.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.33.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.33.input_layernorm": false,
- "model.layers.33.post_attention_layernorm": false,
- "model.layers.34.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.34.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.34.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.34.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.34.self_attn.rope": false,
- "model.layers.34.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.34.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.34.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.34.input_layernorm": false,
- "model.layers.34.post_attention_layernorm": false,
- "model.layers.35.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.35.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.35.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.35.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.35.self_attn.rope": false,
- "model.layers.35.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.35.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.35.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.35.input_layernorm": false,
- "model.layers.35.post_attention_layernorm": false,
- "model.layers.36.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.36.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.36.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.36.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.36.self_attn.rope": false,
- "model.layers.36.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.36.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.36.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.36.input_layernorm": false,
- "model.layers.36.post_attention_layernorm": false,
- "model.layers.37.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.37.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.37.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.37.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.37.self_attn.rope": false,
- "model.layers.37.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.37.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.37.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.37.input_layernorm": false,
- "model.layers.37.post_attention_layernorm": false,
- "model.layers.38.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.38.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.38.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.38.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.38.self_attn.rope": false,
- "model.layers.38.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.38.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.38.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.38.input_layernorm": false,
- "model.layers.38.post_attention_layernorm": false,
- "model.layers.39.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.39.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.39.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.39.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.39.self_attn.rope": false,
- "model.layers.39.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.39.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.39.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.39.input_layernorm": false,
- "model.layers.39.post_attention_layernorm": false,
- "model.layers.40.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.40.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.40.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.40.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.40.self_attn.rope": false,
- "model.layers.40.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.40.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.40.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.40.input_layernorm": false,
- "model.layers.40.post_attention_layernorm": false,
- "model.layers.41.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.41.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.41.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.41.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.41.self_attn.rope": false,
- "model.layers.41.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.41.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.41.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.41.input_layernorm": false,
- "model.layers.41.post_attention_layernorm": false,
- "model.layers.42.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.42.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.42.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.42.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.42.self_attn.rope": false,
- "model.layers.42.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.42.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.42.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.42.input_layernorm": false,
- "model.layers.42.post_attention_layernorm": false,
- "model.layers.43.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.43.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.43.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.43.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.43.self_attn.rope": false,
- "model.layers.43.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.43.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.43.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.43.input_layernorm": false,
- "model.layers.43.post_attention_layernorm": false,
- "model.layers.44.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.44.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.44.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.44.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.44.self_attn.rope": false,
- "model.layers.44.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.44.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.44.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.44.input_layernorm": false,
- "model.layers.44.post_attention_layernorm": false,
- "model.layers.45.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.45.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.45.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.45.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.45.self_attn.rope": false,
- "model.layers.45.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.45.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.45.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.45.input_layernorm": false,
- "model.layers.45.post_attention_layernorm": false,
- "model.layers.46.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.46.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.46.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.46.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.46.self_attn.rope": false,
- "model.layers.46.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.46.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.46.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.46.input_layernorm": false,
- "model.layers.46.post_attention_layernorm": false,
- "model.layers.47.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.47.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.47.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.47.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.47.self_attn.rope": false,
- "model.layers.47.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.47.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.47.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.47.input_layernorm": false,
- "model.layers.47.post_attention_layernorm": false,
- "model.layers.48.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.48.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.48.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.48.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.48.self_attn.rope": false,
- "model.layers.48.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.48.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.48.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.48.input_layernorm": false,
- "model.layers.48.post_attention_layernorm": false,
- "model.layers.49.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.49.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.49.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.49.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.49.self_attn.rope": false,
- "model.layers.49.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.49.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.49.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.49.input_layernorm": false,
- "model.layers.49.post_attention_layernorm": false,
- "model.layers.50.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.50.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.50.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.50.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.50.self_attn.rope": false,
- "model.layers.50.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.50.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.50.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.50.input_layernorm": false,
- "model.layers.50.post_attention_layernorm": false,
- "model.layers.51.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.51.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.51.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.51.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.51.self_attn.rope": false,
- "model.layers.51.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.51.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.51.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.51.input_layernorm": false,
- "model.layers.51.post_attention_layernorm": false,
- "model.layers.52.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.52.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.52.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.52.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.52.self_attn.rope": false,
- "model.layers.52.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.52.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.52.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.52.input_layernorm": false,
- "model.layers.52.post_attention_layernorm": false,
- "model.layers.53.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.53.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.53.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.53.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.53.self_attn.rope": false,
- "model.layers.53.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.53.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.53.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.53.input_layernorm": false,
- "model.layers.53.post_attention_layernorm": false,
- "model.layers.54.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.54.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.54.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.54.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.54.self_attn.rope": false,
- "model.layers.54.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.54.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.54.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.54.input_layernorm": false,
- "model.layers.54.post_attention_layernorm": false,
- "model.layers.55.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.55.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.55.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.55.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.55.self_attn.rope": false,
- "model.layers.55.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.55.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.55.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.55.input_layernorm": false,
- "model.layers.55.post_attention_layernorm": false,
- "model.layers.56.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.56.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.56.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.56.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.56.self_attn.rope": false,
- "model.layers.56.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.56.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.56.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.56.input_layernorm": false,
- "model.layers.56.post_attention_layernorm": false,
- "model.layers.57.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.57.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.57.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.57.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.57.self_attn.rope": false,
- "model.layers.57.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.57.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.57.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.57.input_layernorm": false,
- "model.layers.57.post_attention_layernorm": false,
- "model.layers.58.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.58.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.58.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.58.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.58.self_attn.rope": false,
- "model.layers.58.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.58.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.58.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.58.input_layernorm": false,
- "model.layers.58.post_attention_layernorm": false,
- "model.layers.59.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.59.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.59.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.59.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.59.self_attn.rope": false,
- "model.layers.59.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.59.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.59.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.59.input_layernorm": false,
- "model.layers.59.post_attention_layernorm": false,
- "model.layers.60.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.60.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.60.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.60.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.60.self_attn.rope": false,
- "model.layers.60.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.60.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.60.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.60.input_layernorm": false,
- "model.layers.60.post_attention_layernorm": false,
- "model.layers.61.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.61.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.61.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.61.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.61.self_attn.rope": false,
- "model.layers.61.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.61.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.61.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.61.input_layernorm": false,
- "model.layers.61.post_attention_layernorm": false,
- "model.layers.62.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.62.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.62.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.62.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.62.self_attn.rope": false,
- "model.layers.62.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.62.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.62.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.62.input_layernorm": false,
- "model.layers.62.post_attention_layernorm": false,
- "model.layers.63.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.63.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.63.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.63.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.63.self_attn.rope": false,
- "model.layers.63.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.63.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.63.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.63.input_layernorm": false,
- "model.layers.63.post_attention_layernorm": false,
- "model.norm": false,
- "lm_head": {
- "group_size": 64,
- "bits": 8
- }
- },
- "quantization_config": {
- "group_size": 64,
- "bits": null,
- "model.embed_tokens": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.0.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.0.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.0.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.0.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.0.self_attn.rope": false,
- "model.layers.0.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.0.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.0.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.0.input_layernorm": false,
- "model.layers.0.post_attention_layernorm": false,
- "model.layers.1.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.1.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.1.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.1.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.1.self_attn.rope": false,
- "model.layers.1.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.1.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.1.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.1.input_layernorm": false,
- "model.layers.1.post_attention_layernorm": false,
- "model.layers.2.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.2.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.2.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.2.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.2.self_attn.rope": false,
- "model.layers.2.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.2.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.2.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.2.input_layernorm": false,
- "model.layers.2.post_attention_layernorm": false,
- "model.layers.3.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.3.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.3.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.3.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.3.self_attn.rope": false,
- "model.layers.3.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.3.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.3.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.3.input_layernorm": false,
- "model.layers.3.post_attention_layernorm": false,
- "model.layers.4.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.4.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.4.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.4.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.4.self_attn.rope": false,
- "model.layers.4.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.4.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.4.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.4.input_layernorm": false,
- "model.layers.4.post_attention_layernorm": false,
- "model.layers.5.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.5.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.5.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.5.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.5.self_attn.rope": false,
- "model.layers.5.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.5.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.5.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.5.input_layernorm": false,
- "model.layers.5.post_attention_layernorm": false,
- "model.layers.6.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.6.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.6.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.6.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.6.self_attn.rope": false,
- "model.layers.6.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.6.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.6.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.6.input_layernorm": false,
- "model.layers.6.post_attention_layernorm": false,
- "model.layers.7.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.7.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.7.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.7.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.7.self_attn.rope": false,
- "model.layers.7.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.7.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.7.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.7.input_layernorm": false,
- "model.layers.7.post_attention_layernorm": false,
- "model.layers.8.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.8.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.8.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.8.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.8.self_attn.rope": false,
- "model.layers.8.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.8.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.8.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.8.input_layernorm": false,
- "model.layers.8.post_attention_layernorm": false,
- "model.layers.9.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.9.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.9.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.9.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.9.self_attn.rope": false,
- "model.layers.9.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.9.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.9.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.9.input_layernorm": false,
- "model.layers.9.post_attention_layernorm": false,
- "model.layers.10.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.10.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.10.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.10.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.10.self_attn.rope": false,
- "model.layers.10.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.10.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.10.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.10.input_layernorm": false,
- "model.layers.10.post_attention_layernorm": false,
- "model.layers.11.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.11.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.11.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.11.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.11.self_attn.rope": false,
- "model.layers.11.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.11.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.11.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.11.input_layernorm": false,
- "model.layers.11.post_attention_layernorm": false,
- "model.layers.12.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.12.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.12.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.12.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.12.self_attn.rope": false,
- "model.layers.12.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.12.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.12.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.12.input_layernorm": false,
- "model.layers.12.post_attention_layernorm": false,
- "model.layers.13.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.13.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.13.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.13.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.13.self_attn.rope": false,
- "model.layers.13.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.13.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.13.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.13.input_layernorm": false,
- "model.layers.13.post_attention_layernorm": false,
- "model.layers.14.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.14.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.14.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.14.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.14.self_attn.rope": false,
- "model.layers.14.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.14.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.14.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.14.input_layernorm": false,
- "model.layers.14.post_attention_layernorm": false,
- "model.layers.15.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.15.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.15.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.15.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.15.self_attn.rope": false,
- "model.layers.15.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.15.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.15.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.15.input_layernorm": false,
- "model.layers.15.post_attention_layernorm": false,
- "model.layers.16.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.16.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.16.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.16.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.16.self_attn.rope": false,
- "model.layers.16.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.16.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.16.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.16.input_layernorm": false,
- "model.layers.16.post_attention_layernorm": false,
- "model.layers.17.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.17.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.17.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.17.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.17.self_attn.rope": false,
- "model.layers.17.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.17.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.17.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.17.input_layernorm": false,
- "model.layers.17.post_attention_layernorm": false,
- "model.layers.18.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.18.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.18.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.18.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.18.self_attn.rope": false,
- "model.layers.18.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.18.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.18.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.18.input_layernorm": false,
- "model.layers.18.post_attention_layernorm": false,
- "model.layers.19.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.19.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.19.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.19.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.19.self_attn.rope": false,
- "model.layers.19.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.19.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.19.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.19.input_layernorm": false,
- "model.layers.19.post_attention_layernorm": false,
- "model.layers.20.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.20.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.20.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.20.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.20.self_attn.rope": false,
- "model.layers.20.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.20.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.20.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.20.input_layernorm": false,
- "model.layers.20.post_attention_layernorm": false,
- "model.layers.21.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.21.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.21.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.21.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.21.self_attn.rope": false,
- "model.layers.21.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.21.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.21.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.21.input_layernorm": false,
- "model.layers.21.post_attention_layernorm": false,
- "model.layers.22.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.22.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.22.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.22.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.22.self_attn.rope": false,
- "model.layers.22.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.22.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.22.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.22.input_layernorm": false,
- "model.layers.22.post_attention_layernorm": false,
- "model.layers.23.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.23.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.23.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.23.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.23.self_attn.rope": false,
- "model.layers.23.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.23.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.23.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.23.input_layernorm": false,
- "model.layers.23.post_attention_layernorm": false,
- "model.layers.24.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.24.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.24.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.24.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.24.self_attn.rope": false,
- "model.layers.24.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.24.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.24.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.24.input_layernorm": false,
- "model.layers.24.post_attention_layernorm": false,
- "model.layers.25.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.25.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.25.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.25.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.25.self_attn.rope": false,
- "model.layers.25.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.25.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.25.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.25.input_layernorm": false,
- "model.layers.25.post_attention_layernorm": false,
- "model.layers.26.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.26.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.26.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.26.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.26.self_attn.rope": false,
- "model.layers.26.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.26.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.26.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.26.input_layernorm": false,
- "model.layers.26.post_attention_layernorm": false,
- "model.layers.27.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.27.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.27.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.27.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.27.self_attn.rope": false,
- "model.layers.27.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.27.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.27.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.27.input_layernorm": false,
- "model.layers.27.post_attention_layernorm": false,
- "model.layers.28.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.28.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.28.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.28.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.28.self_attn.rope": false,
- "model.layers.28.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.28.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.28.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.28.input_layernorm": false,
- "model.layers.28.post_attention_layernorm": false,
- "model.layers.29.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.29.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.29.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.29.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.29.self_attn.rope": false,
- "model.layers.29.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.29.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.29.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.29.input_layernorm": false,
- "model.layers.29.post_attention_layernorm": false,
- "model.layers.30.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.30.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.30.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.30.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.30.self_attn.rope": false,
- "model.layers.30.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.30.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.30.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.30.input_layernorm": false,
- "model.layers.30.post_attention_layernorm": false,
- "model.layers.31.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.31.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.31.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.31.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.31.self_attn.rope": false,
- "model.layers.31.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.31.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.31.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.31.input_layernorm": false,
- "model.layers.31.post_attention_layernorm": false,
- "model.layers.32.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.32.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.32.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.32.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.32.self_attn.rope": false,
- "model.layers.32.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.32.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.32.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.32.input_layernorm": false,
- "model.layers.32.post_attention_layernorm": false,
- "model.layers.33.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.33.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.33.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.33.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.33.self_attn.rope": false,
- "model.layers.33.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.33.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.33.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.33.input_layernorm": false,
- "model.layers.33.post_attention_layernorm": false,
- "model.layers.34.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.34.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.34.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.34.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.34.self_attn.rope": false,
- "model.layers.34.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.34.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.34.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.34.input_layernorm": false,
- "model.layers.34.post_attention_layernorm": false,
- "model.layers.35.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.35.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.35.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.35.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.35.self_attn.rope": false,
- "model.layers.35.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.35.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.35.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.35.input_layernorm": false,
- "model.layers.35.post_attention_layernorm": false,
- "model.layers.36.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.36.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.36.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.36.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.36.self_attn.rope": false,
- "model.layers.36.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.36.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.36.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.36.input_layernorm": false,
- "model.layers.36.post_attention_layernorm": false,
- "model.layers.37.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.37.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.37.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.37.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.37.self_attn.rope": false,
- "model.layers.37.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.37.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.37.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.37.input_layernorm": false,
- "model.layers.37.post_attention_layernorm": false,
- "model.layers.38.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.38.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.38.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.38.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.38.self_attn.rope": false,
- "model.layers.38.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.38.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.38.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.38.input_layernorm": false,
- "model.layers.38.post_attention_layernorm": false,
- "model.layers.39.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.39.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.39.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.39.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.39.self_attn.rope": false,
- "model.layers.39.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.39.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.39.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.39.input_layernorm": false,
- "model.layers.39.post_attention_layernorm": false,
- "model.layers.40.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.40.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.40.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.40.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.40.self_attn.rope": false,
- "model.layers.40.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.40.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.40.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.40.input_layernorm": false,
- "model.layers.40.post_attention_layernorm": false,
- "model.layers.41.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.41.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.41.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.41.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.41.self_attn.rope": false,
- "model.layers.41.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.41.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.41.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.41.input_layernorm": false,
- "model.layers.41.post_attention_layernorm": false,
- "model.layers.42.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.42.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.42.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.42.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.42.self_attn.rope": false,
- "model.layers.42.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.42.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.42.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.42.input_layernorm": false,
- "model.layers.42.post_attention_layernorm": false,
- "model.layers.43.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.43.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.43.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.43.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.43.self_attn.rope": false,
- "model.layers.43.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.43.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.43.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.43.input_layernorm": false,
- "model.layers.43.post_attention_layernorm": false,
- "model.layers.44.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.44.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.44.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.44.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.44.self_attn.rope": false,
- "model.layers.44.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.44.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.44.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.44.input_layernorm": false,
- "model.layers.44.post_attention_layernorm": false,
- "model.layers.45.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.45.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.45.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.45.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.45.self_attn.rope": false,
- "model.layers.45.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.45.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.45.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.45.input_layernorm": false,
- "model.layers.45.post_attention_layernorm": false,
- "model.layers.46.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.46.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.46.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.46.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.46.self_attn.rope": false,
- "model.layers.46.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.46.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.46.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.46.input_layernorm": false,
- "model.layers.46.post_attention_layernorm": false,
- "model.layers.47.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.47.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.47.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.47.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.47.self_attn.rope": false,
- "model.layers.47.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.47.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.47.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.47.input_layernorm": false,
- "model.layers.47.post_attention_layernorm": false,
- "model.layers.48.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.48.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.48.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.48.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.48.self_attn.rope": false,
- "model.layers.48.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.48.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.48.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.48.input_layernorm": false,
- "model.layers.48.post_attention_layernorm": false,
- "model.layers.49.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.49.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.49.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.49.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.49.self_attn.rope": false,
- "model.layers.49.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.49.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.49.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.49.input_layernorm": false,
- "model.layers.49.post_attention_layernorm": false,
- "model.layers.50.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.50.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.50.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.50.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.50.self_attn.rope": false,
- "model.layers.50.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.50.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.50.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.50.input_layernorm": false,
- "model.layers.50.post_attention_layernorm": false,
- "model.layers.51.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.51.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.51.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.51.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.51.self_attn.rope": false,
- "model.layers.51.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.51.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.51.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.51.input_layernorm": false,
- "model.layers.51.post_attention_layernorm": false,
- "model.layers.52.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.52.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.52.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.52.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.52.self_attn.rope": false,
- "model.layers.52.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.52.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.52.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.52.input_layernorm": false,
- "model.layers.52.post_attention_layernorm": false,
- "model.layers.53.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.53.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.53.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.53.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.53.self_attn.rope": false,
- "model.layers.53.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.53.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.53.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.53.input_layernorm": false,
- "model.layers.53.post_attention_layernorm": false,
- "model.layers.54.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.54.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.54.self_attn.v_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.54.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.54.self_attn.rope": false,
- "model.layers.54.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.54.mlp.down_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.54.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.54.input_layernorm": false,
- "model.layers.54.post_attention_layernorm": false,
- "model.layers.55.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.55.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.55.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.55.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.55.self_attn.rope": false,
- "model.layers.55.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.55.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.55.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.55.input_layernorm": false,
- "model.layers.55.post_attention_layernorm": false,
- "model.layers.56.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.56.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.56.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.56.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.56.self_attn.rope": false,
- "model.layers.56.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.56.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.56.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.56.input_layernorm": false,
- "model.layers.56.post_attention_layernorm": false,
- "model.layers.57.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.57.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.57.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.57.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.57.self_attn.rope": false,
- "model.layers.57.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.57.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.57.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.57.input_layernorm": false,
- "model.layers.57.post_attention_layernorm": false,
- "model.layers.58.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.58.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.58.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.58.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.58.self_attn.rope": false,
- "model.layers.58.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.58.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.58.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.58.input_layernorm": false,
- "model.layers.58.post_attention_layernorm": false,
- "model.layers.59.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.59.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.59.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.59.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.59.self_attn.rope": false,
- "model.layers.59.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.59.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.59.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.59.input_layernorm": false,
- "model.layers.59.post_attention_layernorm": false,
- "model.layers.60.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.60.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.60.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.60.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.60.self_attn.rope": false,
- "model.layers.60.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.60.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.60.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.60.input_layernorm": false,
- "model.layers.60.post_attention_layernorm": false,
- "model.layers.61.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.61.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.61.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.61.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.61.self_attn.rope": false,
- "model.layers.61.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.61.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.61.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.61.input_layernorm": false,
- "model.layers.61.post_attention_layernorm": false,
- "model.layers.62.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.62.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.62.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.62.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.62.self_attn.rope": false,
- "model.layers.62.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.62.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.62.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.62.input_layernorm": false,
- "model.layers.62.post_attention_layernorm": false,
- "model.layers.63.self_attn.q_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.63.self_attn.k_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.63.self_attn.v_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.63.self_attn.o_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.63.self_attn.rope": false,
- "model.layers.63.mlp.gate_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.63.mlp.down_proj": {
- "group_size": 64,
- "bits": 8
- },
- "model.layers.63.mlp.up_proj": {
- "group_size": 64,
- "bits": 4
- },
- "model.layers.63.input_layernorm": false,
- "model.layers.63.post_attention_layernorm": false,
- "model.norm": false,
- "lm_head": {
- "group_size": 64,
- "bits": 8
- }
- },
- "rms_norm_eps": 1e-05,
- "rope_theta": 1000000.0,
- "sliding_window": 131072,
- "tie_word_embeddings": false,
- "torch_dtype": "bfloat16",
- "transformers_version": "4.43.1",
- "use_cache": true,
- "use_sliding_window": false,
- "vocab_size": 152064
-}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00001-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00001-of-00004.safetensors
deleted file mode 100644
index a25dadeea2fd1bc5aa8d5629ec1f27ed52570c10..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00001-of-00004.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7819f2c0378a7ea9896986fa6f2976101d6dd007bc5b22f5023a148d9a5617b6
-size 5321941889
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00002-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00002-of-00004.safetensors
deleted file mode 100644
index 9eb340a7ed46748d80d946d4e121a19b3aef0dbb..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00002-of-00004.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bd4062e2e1a76c96699e2bdeaab15ce1a130f14f8ff3cc2625dc450e76bd3e96
-size 5363162608
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00003-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00003-of-00004.safetensors
deleted file mode 100644
index 57d7b6c3c8d5c8c0727cc6690a1be3dee451daac..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00003-of-00004.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a23c6fb10dca081039ccca54b9e4101820f55ad2669ba6db700e2d1bd54b81b1
-size 5357249052
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00004-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00004-of-00004.safetensors
deleted file mode 100644
index 2f8e4312262796c34de885c1e9c3f2d60c8d9847..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00004-of-00004.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d849115b9ac769b41689460305df28026834a723b2bf002a132247ef170c09f9
-size 5127218901
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model.safetensors.index.json
deleted file mode 100644
index 9623ba03040e51c3bc211d6df7f30d896026d851..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model.safetensors.index.json
+++ /dev/null
@@ -1,1678 +0,0 @@
-{
- "metadata": {
- "total_size": 21169383424
- },
- "weight_map": {
- "lm_head.biases": "model-00004-of-00004.safetensors",
- "lm_head.scales": "model-00004-of-00004.safetensors",
- "lm_head.weight": "model-00004-of-00004.safetensors",
- "model.embed_tokens.biases": "model-00001-of-00004.safetensors",
- "model.embed_tokens.scales": "model-00001-of-00004.safetensors",
- "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
- "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.0.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.0.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.0.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.0.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.1.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.1.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.1.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.1.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.10.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.10.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.10.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.10.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.11.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.11.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.11.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.11.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.12.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.12.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.12.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.12.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.13.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.13.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.13.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.13.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.14.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.14.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.14.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.14.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.15.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.15.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.15.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.15.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.15.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.15.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.16.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.16.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.16.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.16.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.16.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.16.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.16.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.16.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.16.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.16.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.16.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.16.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.16.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.16.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.17.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.17.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.17.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.17.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.17.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.17.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.17.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.17.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.17.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.17.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.17.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.17.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.17.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.18.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.18.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.18.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.18.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.18.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.18.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.18.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.18.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.18.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.19.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.19.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.19.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.19.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.19.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.19.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.19.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.19.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.19.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.2.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.2.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.2.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.2.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.20.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.20.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.20.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.20.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.20.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.20.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.20.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.20.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.20.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.21.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.21.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.21.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.21.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.21.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.21.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.21.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.21.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.21.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.22.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.22.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.22.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.22.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.22.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.22.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.22.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.22.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.22.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.23.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.23.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.23.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.23.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.23.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.23.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.23.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.23.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.23.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.24.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.24.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.24.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.24.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.24.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.24.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.24.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.24.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.24.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.25.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.25.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.25.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.25.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.25.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.25.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.25.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.25.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.25.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.26.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.26.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.26.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.26.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.26.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.26.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.26.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.26.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.26.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.27.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.27.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.27.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.27.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.27.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.27.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.27.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.27.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.27.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.27.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.28.input_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.28.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.28.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.28.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.28.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.28.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.28.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.28.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.28.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.28.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.28.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.29.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.29.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.29.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.29.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.29.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.29.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.29.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.29.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.29.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.29.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.3.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.3.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.3.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.3.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.30.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.30.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.30.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.30.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.30.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.31.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.31.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.31.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.31.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.31.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.31.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.32.input_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.32.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.32.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.32.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.32.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.32.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.32.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.32.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
- "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.32.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.32.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.32.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.32.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.33.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.33.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.33.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.33.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.33.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.33.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.33.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.33.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.33.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.33.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
- "model.layers.33.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
- "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
- "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
- "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.34.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.34.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.34.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.34.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.34.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.34.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.34.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.34.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.34.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.34.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.34.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.34.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.34.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.34.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.34.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.34.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.34.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.35.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.35.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.35.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.35.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.35.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.35.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.35.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.35.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.35.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.35.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.35.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.35.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.35.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.35.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.36.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.36.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.36.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.36.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.36.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.36.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.36.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.36.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.36.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.36.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.36.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.36.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.36.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.36.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.36.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.36.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.36.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.36.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.36.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.37.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.37.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.37.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.37.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.37.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.37.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.37.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.37.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.37.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.37.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.37.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.37.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.37.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.37.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.37.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.37.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.37.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.37.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.37.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.38.input_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.38.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.38.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.38.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.38.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.38.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.38.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.38.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.38.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.38.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.38.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.38.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.38.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.38.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.38.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.38.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.38.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.38.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.38.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.38.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.39.input_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.39.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.39.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.39.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.39.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.39.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.39.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.39.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.39.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.39.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.39.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.39.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.39.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.39.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.39.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.39.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.39.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.39.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.39.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.39.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.4.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.4.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.4.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.4.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.40.input_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.40.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.40.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.40.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.40.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.40.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.40.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.40.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.40.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.40.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.40.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.40.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.40.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.40.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.40.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.40.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.40.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.40.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.40.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.40.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.40.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.41.input_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.41.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.41.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.41.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.41.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.41.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.41.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.41.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.41.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.41.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.41.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.41.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.41.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.41.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.41.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.41.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.41.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.41.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.41.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.41.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.42.input_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.42.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.42.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.42.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.42.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.42.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.42.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.42.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.42.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.42.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.42.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.42.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.42.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.42.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.42.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.42.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.42.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.42.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.42.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.42.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.42.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.42.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.42.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.42.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.43.input_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.43.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.43.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.43.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.43.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.43.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.43.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.43.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.43.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.43.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.43.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.43.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.43.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.43.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.43.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.43.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.43.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.43.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.43.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.43.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.43.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.43.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.43.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.43.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.43.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.43.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.44.input_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.44.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.44.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.44.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.44.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.44.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.44.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.44.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.44.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.44.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.44.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.44.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.44.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.44.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.44.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.44.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.44.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.44.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.44.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.44.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.44.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.44.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.44.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.44.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.44.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.45.input_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.45.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.45.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.45.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.45.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.45.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.45.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.45.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.45.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.45.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.45.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.45.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.45.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.45.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.45.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.45.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.45.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.45.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.45.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.45.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.45.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.45.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.45.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.46.input_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.46.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.46.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.46.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.46.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.46.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.46.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.46.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.46.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.46.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.46.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.46.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.46.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.46.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.46.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.46.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.46.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.46.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.46.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.46.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.46.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.46.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.46.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.46.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.46.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.47.input_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.47.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.47.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.47.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.47.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.47.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.47.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.47.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.47.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.47.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.47.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.47.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.47.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.47.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.47.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.47.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.47.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.47.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.47.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.47.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.47.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.48.input_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.48.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.48.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.48.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.48.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.48.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.48.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.48.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.48.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.48.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.48.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.48.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.48.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.48.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.48.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.48.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.48.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.48.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.48.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.48.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.48.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.48.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.48.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.48.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.48.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.48.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.49.input_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.49.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.49.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.49.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.49.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.49.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.49.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.49.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.49.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.49.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.49.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.49.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.49.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.49.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.49.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.49.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.49.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.49.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.49.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.49.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.49.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.49.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.49.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.49.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.49.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.5.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.5.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.5.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.5.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.50.input_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.50.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.50.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.50.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.50.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.50.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.50.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.50.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.50.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.50.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.50.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
- "model.layers.50.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.50.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.50.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.50.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.50.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.50.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.50.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.50.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.50.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.50.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.50.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.50.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
- "model.layers.50.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
- "model.layers.50.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
- "model.layers.50.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
- "model.layers.51.input_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.51.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.51.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.51.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.51.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.51.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.51.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.51.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.51.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.51.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.51.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.51.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.51.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.51.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.51.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.51.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.51.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.51.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.51.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.51.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.51.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.51.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.51.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.51.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.51.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.51.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.52.input_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.52.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.52.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.52.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.52.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.52.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.52.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.52.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.52.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.52.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.52.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.52.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.52.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.52.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.52.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.52.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.52.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.52.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.52.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.52.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.52.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.52.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.52.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.52.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.52.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.52.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.53.input_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.53.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.53.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.53.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.53.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.53.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.53.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.53.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.53.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.53.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.53.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.53.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.53.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.53.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.53.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.53.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.53.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.53.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.53.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.53.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.53.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.53.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.53.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.53.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.53.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.53.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.54.input_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.54.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.54.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.54.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.54.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.54.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.54.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.54.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.54.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.54.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.54.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.54.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.54.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.54.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.54.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.54.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.54.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.54.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.54.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.54.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.54.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.54.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.54.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.54.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.54.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.54.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.55.input_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.55.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.55.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.55.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.55.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.55.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.55.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.55.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.55.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.55.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.55.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.55.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.55.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.55.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.55.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.55.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.55.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.55.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.55.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.55.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.55.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.55.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.55.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.55.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.55.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.55.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.56.input_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.56.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.56.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.56.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.56.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.56.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.56.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.56.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.56.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.56.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.56.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.56.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.56.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.56.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.56.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.56.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.56.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.56.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.56.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.56.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.56.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.56.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.56.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.56.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.56.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.56.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.57.input_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.57.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.57.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.57.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.57.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.57.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.57.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.57.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.57.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.57.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.57.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.57.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.57.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.57.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.57.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.57.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.57.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.57.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.57.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.57.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.57.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.57.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.57.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.57.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.57.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.57.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.58.input_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.58.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.58.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.58.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.58.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.58.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.58.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.58.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.58.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.58.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.58.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.58.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.58.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.58.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.58.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.58.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.58.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.58.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.58.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.58.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.58.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.58.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.58.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.58.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.58.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.58.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.59.input_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.59.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.59.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.59.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.59.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.59.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.59.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.59.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.59.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.59.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.59.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.59.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.59.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.59.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.59.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.59.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.59.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.59.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.59.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.59.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.59.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.59.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.59.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.59.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.59.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.59.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.6.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.6.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.6.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.6.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.60.input_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.60.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.60.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.60.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.60.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.60.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.60.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.60.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.60.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.60.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.60.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.60.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.60.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.60.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.60.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.60.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.60.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.60.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.60.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.60.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.60.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.60.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.60.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.60.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.60.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.60.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.61.input_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.61.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.61.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.61.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.61.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.61.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.61.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.61.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.61.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.61.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.61.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.61.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.61.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.61.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.61.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.61.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.61.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.61.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.61.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.61.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.61.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.61.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.61.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.61.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.61.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.61.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.62.input_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.62.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.62.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.62.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.62.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.62.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.62.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.62.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.62.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.62.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.62.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.62.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.62.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.62.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.62.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.62.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.62.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.62.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.62.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.62.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.62.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.62.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.62.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.62.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.62.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.62.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.63.input_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.63.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.63.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.63.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.63.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.63.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.63.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.63.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.63.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.63.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.63.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
- "model.layers.63.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.63.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.63.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.63.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.63.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.63.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.63.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.63.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.63.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.63.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.63.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.63.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
- "model.layers.63.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
- "model.layers.63.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
- "model.layers.63.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
- "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.7.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.7.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.7.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.7.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.8.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.8.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.8.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.8.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.9.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.9.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.9.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.9.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
- "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
- "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
- "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
- "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
- "model.norm.weight": "model-00004-of-00004.safetensors"
- }
-}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/special_tokens_map.json
deleted file mode 100644
index 1d385d62cf08bca35254547902b792c243656ec1..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/special_tokens_map.json
+++ /dev/null
@@ -1,23 +0,0 @@
-{
- "bos_token": {
- "content": "<｜begin▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- },
- "eos_token": {
- "content": "<｜end▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- },
- "pad_token": {
- "content": "<｜end▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- }
-}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/tokenizer.json
deleted file mode 100644
index 1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/tokenizer.json
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
-size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/tokenizer_config.json
deleted file mode 100644
index ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/tokenizer_config.json
+++ /dev/null
@@ -1,195 +0,0 @@
-{
- "add_bos_token": true,
- "add_eos_token": false,
- "add_prefix_space": null,
- "added_tokens_decoder": {
- "151643": {
- "content": "<｜end▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151644": {
- "content": "<｜User｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151645": {
- "content": "<｜Assistant｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151646": {
- "content": "<｜begin▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151647": {
- "content": "<|EOT|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151648": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151649": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151650": {
- "content": "<|quad_start|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151651": {
- "content": "<|quad_end|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151652": {
- "content": "<|vision_start|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151653": {
- "content": "<|vision_end|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151654": {
- "content": "<|vision_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151655": {
- "content": "<|image_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151656": {
- "content": "<|video_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151657": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151658": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151659": {
- "content": "<|fim_prefix|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151660": {
- "content": "<|fim_middle|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151661": {
- "content": "<|fim_suffix|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151662": {
- "content": "<|fim_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151663": {
- "content": "<|repo_name|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151664": {
- "content": "<|file_sep|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- }
- },
- "bos_token": "<｜begin▁of▁sentence｜>",
- "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
- "clean_up_tokenization_spaces": false,
- "eos_token": "<｜end▁of▁sentence｜>",
- "extra_special_tokens": {},
- "legacy": true,
- "model_max_length": 16384,
- "pad_token": "<｜end▁of▁sentence｜>",
- "sp_model_kwargs": {},
- "tokenizer_class": "LlamaTokenizerFast",
- "unk_token": null,
- "use_default_system_prompt": false
-}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B-4bit/special_tokens_map.json
deleted file mode 100644
index 1d385d62cf08bca35254547902b792c243656ec1..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-4bit/special_tokens_map.json
+++ /dev/null
@@ -1,23 +0,0 @@
-{
- "bos_token": {
- "content": "<｜begin▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- },
- "eos_token": {
- "content": "<｜end▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- },
- "pad_token": {
- "content": "<｜end▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- }
-}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B-4bit/tokenizer.json
deleted file mode 100644
index 1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-4bit/tokenizer.json
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
-size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B-4bit/tokenizer_config.json
deleted file mode 100644
index ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-4bit/tokenizer_config.json
+++ /dev/null
@@ -1,195 +0,0 @@
-{
- "add_bos_token": true,
- "add_eos_token": false,
- "add_prefix_space": null,
- "added_tokens_decoder": {
- "151643": {
- "content": "<｜end▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151644": {
- "content": "<｜User｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151645": {
- "content": "<｜Assistant｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151646": {
- "content": "<｜begin▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151647": {
- "content": "<|EOT|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151648": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151649": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151650": {
- "content": "<|quad_start|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151651": {
- "content": "<|quad_end|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151652": {
- "content": "<|vision_start|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151653": {
- "content": "<|vision_end|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151654": {
- "content": "<|vision_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151655": {
- "content": "<|image_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151656": {
- "content": "<|video_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151657": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151658": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151659": {
- "content": "<|fim_prefix|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151660": {
- "content": "<|fim_middle|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151661": {
- "content": "<|fim_suffix|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151662": {
- "content": "<|fim_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151663": {
- "content": "<|repo_name|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151664": {
- "content": "<|file_sep|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- }
- },
- "bos_token": "<｜begin▁of▁sentence｜>",
- "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
- "clean_up_tokenization_spaces": false,
- "eos_token": "<｜end▁of▁sentence｜>",
- "extra_special_tokens": {},
- "legacy": true,
- "model_max_length": 16384,
- "pad_token": "<｜end▁of▁sentence｜>",
- "sp_model_kwargs": {},
- "tokenizer_class": "LlamaTokenizerFast",
- "unk_token": null,
- "use_default_system_prompt": false
-}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/config.json b/DeepSeek-R1-Distill-Qwen-32B-6bit/config.json
deleted file mode 100644
index 1ae0ef50e634d8a07427dc5e1136746dd21473ac..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-6bit/config.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
- "architectures": [
- "Qwen2ForCausalLM"
- ],
- "attention_dropout": 0.0,
- "bos_token_id": 151643,
- "eos_token_id": 151643,
- "hidden_act": "silu",
- "hidden_size": 5120,
- "initializer_range": 0.02,
- "intermediate_size": 27648,
- "max_position_embeddings": 131072,
- "max_window_layers": 64,
- "model_type": "qwen2",
- "num_attention_heads": 40,
- "num_hidden_layers": 64,
- "num_key_value_heads": 8,
- "quantization": {
- "group_size": 64,
- "bits": 6
- },
- "quantization_config": {
- "group_size": 64,
- "bits": 6
- },
- "rms_norm_eps": 1e-05,
- "rope_theta": 1000000.0,
- "sliding_window": 131072,
- "tie_word_embeddings": false,
- "torch_dtype": "bfloat16",
- "transformers_version": "4.43.1",
- "use_cache": true,
- "use_sliding_window": false,
- "vocab_size": 152064
-}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00001-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00001-of-00006.safetensors
deleted file mode 100644
index bd50ccc10416b584575792d741743e4ffa7d2286..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00001-of-00006.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9a00935ed67ac7e66d142d5f9e4815eb8ab3f961faa7b8bcbca55a4ff2f4ee25
-size 5271984209
diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00002-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00002-of-00006.safetensors
deleted file mode 100644
index 35b735b757d7980e58f65e1311d988d9e7d75de9..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00002-of-00006.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5e09753f33189775b86554c9737eb5574dbd556dd476966ee69cccdb0eb89517
-size 5316808320
diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00003-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00003-of-00006.safetensors
deleted file mode 100644
index 37d4cdd24df8ae7e352ca68c2cc7849c9a6a4446..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00003-of-00006.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7c40d6060b390eac2274cb2d18973e8fc4ef5747e4d5ae60b2c7a6f0fc8505fb
-size 5265653517
diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00004-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00004-of-00006.safetensors
deleted file mode 100644
index ff80a953c7723fc0cae5770b20b55c43de3b976f..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00004-of-00006.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f81a6a9069dda4ded4f7043ef63966d113d9534180fa561fa25ffa21ab646479
-size 5265653541
diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00005-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00005-of-00006.safetensors
deleted file mode 100644
index d136bca71b10ba8fe0ad61f039b66a331935d7a3..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00005-of-00006.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7a88fe01f535a1e4316b000d0f5322482e33e598003500c39bf174a4cee86ed1
-size 4869481603
diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00006-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00006-of-00006.safetensors
deleted file mode 100644
index a8676dc07afffbbc5fe7b41db3ad6d308576b05b..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00006-of-00006.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:04c494df573aaf13437bb7e389e37e2ab8b602836efb826cb3178bf4b125d1e0
-size 632586540
diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B-6bit/model.safetensors.index.json
deleted file mode 100644
index b5e942aa358d06cce6e319fcc937a4e0a92158ac..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-6bit/model.safetensors.index.json
+++ /dev/null
@@ -1,1678 +0,0 @@
-{
- "metadata": {
- "total_size": 26621978624
- },
- "weight_map": {
- "lm_head.biases": "model-00006-of-00006.safetensors",
- "lm_head.scales": "model-00006-of-00006.safetensors",
- "lm_head.weight": "model-00006-of-00006.safetensors",
- "model.embed_tokens.biases": "model-00001-of-00006.safetensors",
- "model.embed_tokens.scales": "model-00001-of-00006.safetensors",
- "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
- "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
- "model.layers.0.mlp.down_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.0.mlp.down_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.0.mlp.up_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.0.mlp.up_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
- "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
- "model.layers.1.mlp.down_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.1.mlp.down_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.1.mlp.up_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.1.mlp.up_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
- "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.10.input_layernorm.weight": "model-00001-of-00006.safetensors",
- "model.layers.10.mlp.down_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.10.mlp.down_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.10.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.10.mlp.up_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.10.mlp.up_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
- "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.11.mlp.down_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.11.mlp.down_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.11.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.11.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.11.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.12.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.12.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.12.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.12.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.12.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.12.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.12.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.12.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.12.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.12.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.12.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.12.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.12.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.12.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.13.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.13.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.13.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.13.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.13.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.13.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.13.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.13.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.13.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.13.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.13.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.13.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.13.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.13.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.14.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.14.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.14.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.14.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.14.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.14.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.14.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.14.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.14.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.14.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.14.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.14.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.14.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.14.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.15.input_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.15.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.15.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.15.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.15.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.15.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.15.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.15.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.15.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.15.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.15.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.15.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.15.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.15.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.15.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.15.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.15.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.16.input_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.16.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.16.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.16.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.16.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.16.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.16.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.16.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.16.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.16.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.16.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.16.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.16.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.16.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.16.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.16.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.16.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.17.input_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.17.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.17.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.17.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.17.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.17.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.17.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.17.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.17.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.17.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.17.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.17.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.17.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.17.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.17.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.17.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.18.input_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.18.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.18.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.18.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.18.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.18.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.18.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.18.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.18.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.18.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.18.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.18.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.19.input_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.19.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.19.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.19.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.19.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.19.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.19.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.19.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.19.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.19.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.19.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.19.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
- "model.layers.2.mlp.down_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.2.mlp.down_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.2.mlp.up_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.2.mlp.up_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
- "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.20.input_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.20.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.20.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.20.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.20.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.20.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.20.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.20.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.20.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.20.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.20.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.20.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.21.input_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.21.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.21.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.21.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.21.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.21.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.21.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.21.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.21.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.21.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.21.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.21.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.22.input_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.22.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.22.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.22.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.22.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.22.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.22.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.22.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.22.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.22.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.22.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.22.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.23.input_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.23.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.23.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.23.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.23.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.23.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.23.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.23.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.23.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.23.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.23.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.23.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.24.input_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.24.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.24.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.24.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.24.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.24.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.24.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.24.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
- "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.24.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.24.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.24.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.24.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.25.input_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.25.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.25.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.25.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.25.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.25.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.25.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.25.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.25.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.25.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.25.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.25.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
- "model.layers.25.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
- "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
- "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
- "model.layers.26.input_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.26.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.26.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.26.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.26.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.26.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.26.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.26.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.26.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.26.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.26.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.26.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.26.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.26.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.26.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.26.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.26.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.27.input_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.27.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.27.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.27.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.27.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.27.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.27.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.27.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.27.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.27.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.27.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.27.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.27.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.27.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.27.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.27.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.27.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.28.input_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.28.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.28.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.28.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.28.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.28.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.28.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.28.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.28.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.28.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.28.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.28.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.28.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.28.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.28.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.28.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.28.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.28.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.28.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.28.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.29.input_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.29.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.29.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.29.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.29.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.29.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.29.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.29.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.29.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.29.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.29.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.29.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.29.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.29.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.29.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.29.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.29.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.29.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.29.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.29.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
- "model.layers.3.mlp.down_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.3.mlp.down_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.3.mlp.up_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.3.mlp.up_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
- "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.30.input_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.30.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.30.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.30.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.30.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.30.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.30.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.30.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.30.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.30.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.30.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.30.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.30.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.30.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.30.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.30.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.30.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.30.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.30.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.30.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.31.input_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.31.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.31.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.31.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.31.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.31.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.31.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.31.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.31.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.31.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.31.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.31.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.31.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.31.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.31.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.31.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.31.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.32.input_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.32.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.32.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.32.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.32.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.32.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.32.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.32.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.32.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.32.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.32.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.32.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.32.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.32.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.32.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.32.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.32.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.32.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.32.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.32.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.33.input_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.33.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.33.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.33.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.33.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.33.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.33.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.33.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.33.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.33.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.33.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.33.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.33.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.33.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.33.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.33.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.33.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.33.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.33.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.33.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.34.input_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.34.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.34.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.34.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.34.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.34.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.34.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.34.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.34.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.34.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.34.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.34.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.34.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.34.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.34.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.34.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.34.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.34.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.34.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.34.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.35.input_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.35.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.35.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.35.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.35.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.35.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.35.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.35.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.35.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.35.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.35.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.35.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.35.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.35.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.35.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.35.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.35.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.36.input_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.36.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.36.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.36.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.36.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.36.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.36.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.36.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.36.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.36.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.36.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.36.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.36.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.36.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.36.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.36.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.36.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.36.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.36.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.36.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.37.input_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.37.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.37.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.37.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.37.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.37.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.37.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.37.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.37.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
- "model.layers.37.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.37.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.37.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.37.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.37.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.37.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.37.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.37.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.37.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.37.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.37.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.38.input_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.38.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.38.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.38.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.38.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.38.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.38.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.38.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.38.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.38.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.38.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.38.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.38.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.38.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.38.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.38.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.38.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.38.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
- "model.layers.38.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
- "model.layers.38.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
- "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
- "model.layers.39.input_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.39.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.39.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.39.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.39.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.39.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.39.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.39.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.39.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.39.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.39.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.39.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.39.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.39.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.39.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.39.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.39.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.39.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.39.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.39.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
- "model.layers.4.mlp.down_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.4.mlp.down_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.4.mlp.up_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.4.mlp.up_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
- "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.40.input_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.40.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.40.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.40.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.40.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.40.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.40.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.40.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.40.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.40.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.40.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.40.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.40.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.40.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.40.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.40.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.40.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.40.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.40.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.40.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.41.input_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.41.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.41.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.41.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.41.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.41.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.41.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.41.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.41.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.41.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.41.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.41.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.41.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.41.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.41.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.41.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.41.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.41.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.41.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.41.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.42.input_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.42.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.42.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.42.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.42.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.42.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.42.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.42.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.42.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.42.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.42.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.42.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.42.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.42.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.42.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.42.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.42.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.42.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.42.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.42.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.42.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.42.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.42.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.43.input_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.43.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.43.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.43.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.43.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.43.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.43.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.43.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.43.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.43.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.43.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.43.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.43.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.43.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.43.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.43.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.43.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.43.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.43.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.43.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.43.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.43.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.43.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.43.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.44.input_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.44.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.44.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.44.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.44.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.44.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.44.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.44.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.44.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.44.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.44.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.44.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.44.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.44.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.44.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.44.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.44.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.44.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.44.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.44.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.44.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.44.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.44.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.44.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.44.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.44.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.45.input_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.45.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.45.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.45.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.45.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.45.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.45.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.45.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.45.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.45.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.45.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.45.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.45.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.45.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.45.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.45.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.45.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.45.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.45.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.45.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.45.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.45.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.45.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.45.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.45.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.45.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.46.input_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.46.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.46.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.46.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.46.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.46.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.46.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.46.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.46.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.46.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.46.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.46.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.46.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.46.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.46.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.46.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.46.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.46.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.46.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.46.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.46.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.46.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.46.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.46.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.46.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.46.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.47.input_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.47.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.47.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.47.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.47.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.47.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.47.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.47.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.47.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.47.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.47.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.47.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.47.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.47.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.47.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.47.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.47.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.47.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.47.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.47.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.47.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.47.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.47.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.47.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.47.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.47.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.48.input_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.48.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.48.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.48.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.48.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.48.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.48.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.48.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.48.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.48.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.48.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.48.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.48.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.48.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.48.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.48.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.48.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.48.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.48.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.48.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.48.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.48.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.48.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.48.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.48.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.48.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.49.input_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.49.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.49.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.49.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.49.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.49.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.49.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.49.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.49.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.49.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.49.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.49.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.49.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.49.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.49.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.49.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.49.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.49.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.49.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.49.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.49.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.49.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.49.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.49.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.49.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.49.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
- "model.layers.5.mlp.down_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.5.mlp.down_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.5.mlp.up_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.5.mlp.up_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
- "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.50.input_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.50.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.50.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.50.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.50.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.50.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.50.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.50.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.50.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.50.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.50.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
- "model.layers.50.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.50.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.50.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.50.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.50.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.50.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.50.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.50.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.50.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.50.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.50.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.50.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.50.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.50.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.50.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.51.input_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.51.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.51.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.51.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.51.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.51.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.51.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.51.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.51.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.51.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.51.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.51.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.51.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.51.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.51.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.51.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.51.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.51.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.51.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.51.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.51.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.51.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.51.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
- "model.layers.51.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
- "model.layers.51.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
- "model.layers.51.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
- "model.layers.52.input_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.52.mlp.down_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.52.mlp.down_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.52.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.52.mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.52.mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.52.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.52.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.52.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.52.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.52.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.52.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.52.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.52.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.52.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.52.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.52.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.52.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.52.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.52.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.52.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.52.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.52.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.52.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.52.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.52.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.53.input_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.53.mlp.down_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.53.mlp.down_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.53.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.53.mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.53.mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.53.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.53.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.53.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.53.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.53.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.53.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.53.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.53.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.53.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.53.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.53.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.53.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.53.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.53.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.53.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.53.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.53.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.53.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.53.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.53.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.54.input_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.54.mlp.down_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.54.mlp.down_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.54.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.54.mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.54.mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.54.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.54.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.54.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.54.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.54.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.54.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.54.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.54.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.54.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.54.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.54.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.54.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.54.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.54.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.54.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.54.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.54.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.54.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.54.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.54.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.55.input_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.55.mlp.down_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.55.mlp.down_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.55.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.55.mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.55.mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.55.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.55.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.55.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.55.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.55.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.55.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.55.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.55.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.55.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.55.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.55.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.55.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.55.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.55.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.55.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.55.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.55.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.55.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.55.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.55.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.56.input_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.56.mlp.down_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.56.mlp.down_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.56.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.56.mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.56.mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.56.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.56.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.56.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.56.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.56.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.56.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.56.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.56.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.56.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.56.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.56.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.56.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.56.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.56.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.56.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.56.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.56.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.56.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.56.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.56.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.57.input_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.57.mlp.down_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.57.mlp.down_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.57.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.57.mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.57.mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.57.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.57.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.57.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.57.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.57.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.57.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.57.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.57.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.57.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.57.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.57.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.57.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.57.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.57.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.57.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.57.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.57.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.57.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.57.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.57.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.58.input_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.58.mlp.down_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.58.mlp.down_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.58.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.58.mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.58.mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.58.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.58.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.58.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.58.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.58.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.58.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.58.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.58.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.58.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.58.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.58.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.58.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.58.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.58.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.58.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.58.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.58.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.58.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.58.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.58.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.59.input_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.59.mlp.down_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.59.mlp.down_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.59.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.59.mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.59.mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.59.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.59.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.59.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.59.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.59.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.59.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.59.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.59.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.59.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.59.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.59.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.59.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.59.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.59.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.59.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.59.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.59.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.59.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.59.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.59.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.6.input_layernorm.weight": "model-00001-of-00006.safetensors",
- "model.layers.6.mlp.down_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.6.mlp.down_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.6.mlp.up_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.6.mlp.up_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
- "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.60.input_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.60.mlp.down_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.60.mlp.down_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.60.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.60.mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.60.mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.60.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.60.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.60.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.60.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.60.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.60.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.60.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.60.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.60.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.60.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.60.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.60.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.60.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.60.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.60.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.60.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.60.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.60.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.60.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.60.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.61.input_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.61.mlp.down_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.61.mlp.down_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.61.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.61.mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.61.mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.61.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.61.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.61.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.61.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.61.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.61.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.61.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.61.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.61.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.61.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.61.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.61.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.61.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.61.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.61.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.61.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.61.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.61.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.61.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.61.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.62.input_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.62.mlp.down_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.62.mlp.down_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.62.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.62.mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.62.mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.62.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.62.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.62.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.62.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.62.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.62.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.62.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.62.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.62.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.62.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.62.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.62.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.62.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.62.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.62.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.62.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.62.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.62.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.62.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.62.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.63.input_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.63.mlp.down_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.63.mlp.down_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.63.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.63.mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.63.mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.63.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.63.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.63.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.63.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.63.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
- "model.layers.63.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.63.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.63.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.63.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.63.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.63.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.63.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.63.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.63.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.63.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.63.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.63.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
- "model.layers.63.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
- "model.layers.63.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
- "model.layers.63.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
- "model.layers.7.input_layernorm.weight": "model-00001-of-00006.safetensors",
- "model.layers.7.mlp.down_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.7.mlp.down_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.7.mlp.up_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.7.mlp.up_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
- "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.8.input_layernorm.weight": "model-00001-of-00006.safetensors",
- "model.layers.8.mlp.down_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.8.mlp.down_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.8.mlp.up_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.8.mlp.up_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
- "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.9.input_layernorm.weight": "model-00001-of-00006.safetensors",
- "model.layers.9.mlp.down_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.9.mlp.down_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.9.mlp.up_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.9.mlp.up_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
- "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
- "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
- "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
- "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
- "model.norm.weight": "model-00005-of-00006.safetensors"
- }
-}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B-6bit/special_tokens_map.json
deleted file mode 100644
index 1d385d62cf08bca35254547902b792c243656ec1..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-6bit/special_tokens_map.json
+++ /dev/null
@@ -1,23 +0,0 @@
-{
- "bos_token": {
- "content": "<｜begin▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- },
- "eos_token": {
- "content": "<｜end▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- },
- "pad_token": {
- "content": "<｜end▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- }
-}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B-6bit/tokenizer.json
deleted file mode 100644
index 1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-6bit/tokenizer.json
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
-size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B-6bit/tokenizer_config.json
deleted file mode 100644
index ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-6bit/tokenizer_config.json
+++ /dev/null
@@ -1,195 +0,0 @@
-{
- "add_bos_token": true,
- "add_eos_token": false,
- "add_prefix_space": null,
- "added_tokens_decoder": {
- "151643": {
- "content": "<｜end▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151644": {
- "content": "<｜User｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151645": {
- "content": "<｜Assistant｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151646": {
- "content": "<｜begin▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151647": {
- "content": "<|EOT|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151648": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151649": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151650": {
- "content": "<|quad_start|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151651": {
- "content": "<|quad_end|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151652": {
- "content": "<|vision_start|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151653": {
- "content": "<|vision_end|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151654": {
- "content": "<|vision_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151655": {
- "content": "<|image_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151656": {
- "content": "<|video_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151657": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151658": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151659": {
- "content": "<|fim_prefix|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151660": {
- "content": "<|fim_middle|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151661": {
- "content": "<|fim_suffix|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151662": {
- "content": "<|fim_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151663": {
- "content": "<|repo_name|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151664": {
- "content": "<|file_sep|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- }
- },
- "bos_token": "<｜begin▁of▁sentence｜>",
- "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
- "clean_up_tokenization_spaces": false,
- "eos_token": "<｜end▁of▁sentence｜>",
- "extra_special_tokens": {},
- "legacy": true,
- "model_max_length": 16384,
- "pad_token": "<｜end▁of▁sentence｜>",
- "sp_model_kwargs": {},
- "tokenizer_class": "LlamaTokenizerFast",
- "unk_token": null,
- "use_default_system_prompt": false
-}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/config.json b/DeepSeek-R1-Distill-Qwen-32B-8bit/config.json
deleted file mode 100644
index 9739a1aa9f8d7a19f46016b2bb951fc94337af27..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-8bit/config.json
+++ /dev/null
@@ -1,35 +0,0 @@
-{
- "architectures": [
- "Qwen2ForCausalLM"
- ],
- "attention_dropout": 0.0,
- "bos_token_id": 151643,
- "eos_token_id": 151643,
- "hidden_act": "silu",
- "hidden_size": 5120,
- "initializer_range": 0.02,
- "intermediate_size": 27648,
- "max_position_embeddings": 131072,
- "max_window_layers": 64,
- "model_type": "qwen2",
- "num_attention_heads": 40,
- "num_hidden_layers": 64,
- "num_key_value_heads": 8,
- "quantization": {
- "group_size": 64,
- "bits": 8
- },
- "quantization_config": {
- "group_size": 64,
- "bits": 8
- },
- "rms_norm_eps": 1e-05,
- "rope_theta": 1000000.0,
- "sliding_window": 131072,
- "tie_word_embeddings": false,
- "torch_dtype": "bfloat16",
- "transformers_version": "4.43.1",
- "use_cache": true,
- "use_sliding_window": false,
- "vocab_size": 152064
-}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00001-of-00007.safetensors b/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00001-of-00007.safetensors
deleted file mode 100644
index 9808909775cdd67c78f3a9d654e8169afa847add..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00001-of-00007.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8f49f3c007b150fac67e909703d4c80223091b1df5c89f925eb56d03f77128ec
-size 5339700785
diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00002-of-00007.safetensors b/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00002-of-00007.safetensors
deleted file mode 100644
index b825fffa5f134ec6b827f3b27df02813ee80c970..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00002-of-00007.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ed1608e9292d3d14e98226291362dedac258b3f14cc1c0ece7cd3c797ff1b0c4
-size 5364861187
diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00003-of-00007.safetensors b/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00003-of-00007.safetensors
deleted file mode 100644
index 77e53de96ea8ece9beed4a833e8da1acae9ad793..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00003-of-00007.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7878ee4f5cbb3e15757a7e4f95d4fa1d034ff7a988e3daadb030f448da0ccce9
-size 5364830173
diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00004-of-00007.safetensors b/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00004-of-00007.safetensors
deleted file mode 100644
index 4def0752bd15fc674a9bdfe0fe6253abe1b8a74c..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00004-of-00007.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a80fef18c69aee587c2f5490988e9d0de9313c2e542a34b6a37a359211749f1d
-size 5331404024
diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00005-of-00007.safetensors b/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00005-of-00007.safetensors
deleted file mode 100644
index a30be962265eaa51571b0b3c6a7bffd7f58457b6..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00005-of-00007.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:49cf366d67b61a144e4afa4413250331adec2893a6dc0d72ae891748bf398c68
-size 5364861246
diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00006-of-00007.safetensors b/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00006-of-00007.safetensors
deleted file mode 100644
index dec9cce32318be547ef672ea901f9a2d60d7f86d..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00006-of-00007.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3d91a1d6d78354bc4a9ee2c9008c606e2033a078ec0b62e701378a66355b177e
-size 5364830197
diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00007-of-00007.safetensors b/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00007-of-00007.safetensors
deleted file mode 100644
index ce8b895cafe1f879138bd77e752783cf8f30e694..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00007-of-00007.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ec29dea35ff6a109994e8199585b7264c37f2d653fb17a0e0d752e77de7d2bf4
-size 2682369911
diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B-8bit/model.safetensors.index.json
deleted file mode 100644
index d5b2be0027e822f018604558746e44a538b7d292..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-8bit/model.safetensors.index.json
+++ /dev/null
@@ -1,1678 +0,0 @@
-{
- "metadata": {
- "total_size": 34812667904
- },
- "weight_map": {
- "lm_head.biases": "model-00007-of-00007.safetensors",
- "lm_head.scales": "model-00007-of-00007.safetensors",
- "lm_head.weight": "model-00007-of-00007.safetensors",
- "model.embed_tokens.biases": "model-00001-of-00007.safetensors",
- "model.embed_tokens.scales": "model-00001-of-00007.safetensors",
- "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
- "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
- "model.layers.0.mlp.down_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.0.mlp.down_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.0.mlp.up_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.0.mlp.up_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
- "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
- "model.layers.1.mlp.down_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.1.mlp.down_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.1.mlp.up_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.1.mlp.up_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
- "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
- "model.layers.10.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.10.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.10.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.10.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.10.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.10.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
- "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.10.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.10.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.10.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.10.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.10.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.10.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.10.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.10.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
- "model.layers.11.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.11.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.11.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.11.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.11.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.11.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
- "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.11.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.11.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.11.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.11.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.11.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.11.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.11.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.11.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
- "model.layers.12.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.12.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.12.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.12.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.12.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.12.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
- "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.12.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.12.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.12.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.12.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.12.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.12.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.12.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.12.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors",
- "model.layers.13.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.13.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.13.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.13.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.13.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.13.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
- "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.13.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.13.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.13.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.13.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.13.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.13.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.13.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.13.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors",
- "model.layers.14.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.14.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.14.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.14.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.14.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.14.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.14.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.14.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
- "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.14.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.14.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.14.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.14.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.14.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.14.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.14.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.14.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors",
- "model.layers.15.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.15.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.15.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.15.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.15.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.15.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.15.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.15.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
- "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.15.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.15.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.15.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.15.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.15.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.15.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.15.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.15.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.16.input_layernorm.weight": "model-00002-of-00007.safetensors",
- "model.layers.16.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.16.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.16.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.16.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.16.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.16.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.16.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.16.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
- "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.16.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.16.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.16.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.16.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.16.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.16.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.16.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.16.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.17.input_layernorm.weight": "model-00002-of-00007.safetensors",
- "model.layers.17.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.17.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.17.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.17.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.17.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.17.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.17.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.17.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
- "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.17.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.17.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.17.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.17.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.17.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.17.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.17.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.18.input_layernorm.weight": "model-00002-of-00007.safetensors",
- "model.layers.18.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.18.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.18.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.18.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.18.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.18.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.18.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
- "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.18.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.18.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.18.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.18.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors",
- "model.layers.19.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.19.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.19.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.19.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.19.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.19.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
- "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.19.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.19.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.19.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.19.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.19.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.19.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
- "model.layers.2.mlp.down_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.2.mlp.down_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.2.mlp.up_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.2.mlp.up_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
- "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors",
- "model.layers.20.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.20.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.20.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.20.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.20.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.20.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
- "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.20.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.20.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.20.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.20.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.20.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.20.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.20.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.20.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors",
- "model.layers.21.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.21.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.21.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.21.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.21.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.21.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
- "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.21.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.21.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.21.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.21.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.21.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.21.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.21.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.21.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors",
- "model.layers.22.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.22.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.22.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.22.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.22.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.22.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
- "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.22.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.22.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.22.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.22.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.22.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.22.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.22.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.22.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.23.input_layernorm.weight": "model-00003-of-00007.safetensors",
- "model.layers.23.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.23.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.23.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.23.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.23.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.23.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.23.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.23.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
- "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.23.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.23.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.23.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.23.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.23.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.23.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.23.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.23.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.24.input_layernorm.weight": "model-00003-of-00007.safetensors",
- "model.layers.24.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.24.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.24.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.24.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.24.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.24.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.24.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.24.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
- "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.24.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.24.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.24.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.24.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.24.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.24.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.24.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.24.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.25.input_layernorm.weight": "model-00003-of-00007.safetensors",
- "model.layers.25.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.25.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.25.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.25.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.25.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.25.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.25.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.25.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
- "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.25.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.25.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.25.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.25.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.25.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.25.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.25.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.25.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.26.input_layernorm.weight": "model-00003-of-00007.safetensors",
- "model.layers.26.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.26.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.26.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.26.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.26.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.26.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.26.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.26.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
- "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.26.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.26.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.26.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.26.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.26.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.26.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.26.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.26.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.27.input_layernorm.weight": "model-00003-of-00007.safetensors",
- "model.layers.27.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.27.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.27.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.27.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.27.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.27.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.27.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.27.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
- "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.27.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.27.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.27.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.27.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.27.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.27.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.27.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.27.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.28.input_layernorm.weight": "model-00003-of-00007.safetensors",
- "model.layers.28.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.28.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.28.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.28.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.28.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.28.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.28.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.28.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
- "model.layers.28.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.28.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.28.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.28.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.28.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.28.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.28.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.28.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.28.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.28.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.28.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors",
- "model.layers.29.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.29.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.29.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.29.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.29.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.29.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.29.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.29.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
- "model.layers.29.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.29.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.29.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.29.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.29.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.29.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.29.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.29.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.29.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
- "model.layers.29.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
- "model.layers.29.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
- "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
- "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
- "model.layers.3.mlp.down_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.3.mlp.down_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.3.mlp.up_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.3.mlp.up_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
- "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors",
- "model.layers.30.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.30.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.30.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.30.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.30.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.30.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.30.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.30.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
- "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.30.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.30.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.30.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.30.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.30.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.30.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.30.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.30.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors",
- "model.layers.31.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.31.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.31.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.31.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.31.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.31.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.31.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.31.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
- "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.31.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.31.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.31.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.31.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.31.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.31.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.31.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.31.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.32.input_layernorm.weight": "model-00004-of-00007.safetensors",
- "model.layers.32.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.32.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.32.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.32.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.32.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.32.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.32.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.32.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
- "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.32.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.32.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.32.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.32.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.32.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.32.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.32.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.32.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.33.input_layernorm.weight": "model-00004-of-00007.safetensors",
- "model.layers.33.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.33.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.33.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.33.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.33.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.33.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.33.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.33.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
- "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.33.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.33.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.33.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.33.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.33.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.33.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.33.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.33.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.34.input_layernorm.weight": "model-00004-of-00007.safetensors",
- "model.layers.34.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.34.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.34.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.34.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.34.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.34.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.34.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.34.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
- "model.layers.34.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.34.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.34.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.34.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.34.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.34.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.34.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.34.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.34.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.34.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.34.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.35.input_layernorm.weight": "model-00004-of-00007.safetensors",
- "model.layers.35.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.35.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.35.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.35.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.35.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.35.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.35.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.35.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
- "model.layers.35.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.35.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.35.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.35.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.35.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.35.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.35.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.35.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.35.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.35.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.35.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.36.input_layernorm.weight": "model-00004-of-00007.safetensors",
- "model.layers.36.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.36.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.36.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.36.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.36.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.36.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.36.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.36.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
- "model.layers.36.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.36.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.36.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.36.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.36.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.36.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.36.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.36.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.36.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.36.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.36.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.37.input_layernorm.weight": "model-00004-of-00007.safetensors",
- "model.layers.37.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.37.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.37.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.37.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.37.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.37.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.37.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.37.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
- "model.layers.37.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.37.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.37.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.37.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.37.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.37.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.37.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.37.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.37.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.37.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.37.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.38.input_layernorm.weight": "model-00004-of-00007.safetensors",
- "model.layers.38.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.38.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.38.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.38.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.38.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.38.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.38.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.38.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
- "model.layers.38.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.38.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.38.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.38.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.38.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.38.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.38.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.38.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.38.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.38.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.38.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.39.input_layernorm.weight": "model-00005-of-00007.safetensors",
- "model.layers.39.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.39.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.39.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.39.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.39.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.39.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.39.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.39.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
- "model.layers.39.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.39.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.39.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.39.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.39.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.39.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.39.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.39.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.39.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
- "model.layers.39.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
- "model.layers.39.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
- "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
- "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
- "model.layers.4.mlp.down_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.4.mlp.down_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.4.mlp.up_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.4.mlp.up_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
- "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.40.input_layernorm.weight": "model-00005-of-00007.safetensors",
- "model.layers.40.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.40.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.40.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.40.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.40.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.40.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.40.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.40.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
- "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.40.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.40.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.40.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.40.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.40.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.40.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.40.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.40.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.41.input_layernorm.weight": "model-00005-of-00007.safetensors",
- "model.layers.41.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.41.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.41.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.41.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.41.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.41.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.41.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.41.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
- "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.41.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.41.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.41.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.41.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.41.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.41.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.41.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.41.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.42.input_layernorm.weight": "model-00005-of-00007.safetensors",
- "model.layers.42.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.42.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.42.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.42.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.42.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.42.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.42.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.42.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
- "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.42.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.42.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.42.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.42.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.42.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.42.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.42.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.42.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.43.input_layernorm.weight": "model-00005-of-00007.safetensors",
- "model.layers.43.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.43.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.43.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.43.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.43.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.43.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.43.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.43.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
- "model.layers.43.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.43.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.43.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.43.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.43.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.43.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.43.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.43.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.43.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.43.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.43.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.44.input_layernorm.weight": "model-00005-of-00007.safetensors",
- "model.layers.44.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.44.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.44.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.44.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.44.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.44.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.44.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.44.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.44.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
- "model.layers.44.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.44.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.44.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.44.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.44.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.44.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.44.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.44.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.44.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.44.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.44.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.44.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.44.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.44.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.45.input_layernorm.weight": "model-00005-of-00007.safetensors",
- "model.layers.45.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.45.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.45.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.45.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.45.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.45.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.45.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.45.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.45.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
- "model.layers.45.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.45.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.45.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.45.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.45.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.45.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.45.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.45.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.45.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.45.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.45.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.45.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.46.input_layernorm.weight": "model-00005-of-00007.safetensors",
- "model.layers.46.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.46.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.46.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.46.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.46.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.46.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.46.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.46.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.46.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.46.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
- "model.layers.46.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.46.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.46.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.46.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.46.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.46.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.46.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.46.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.46.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.46.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.46.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.46.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.46.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.46.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.46.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.47.input_layernorm.weight": "model-00005-of-00007.safetensors",
- "model.layers.47.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.47.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.47.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.47.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.47.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.47.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.47.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.47.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.47.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.47.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
- "model.layers.47.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.47.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.47.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.47.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.47.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.47.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.47.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.47.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.47.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.47.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.47.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.47.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.47.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.47.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.47.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.48.input_layernorm.weight": "model-00005-of-00007.safetensors",
- "model.layers.48.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.48.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.48.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.48.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.48.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.48.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.48.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.48.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.48.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.48.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
- "model.layers.48.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.48.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.48.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.48.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.48.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.48.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.48.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.48.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.48.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.48.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.48.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.48.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.48.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.48.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.48.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.49.input_layernorm.weight": "model-00005-of-00007.safetensors",
- "model.layers.49.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.49.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.49.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.49.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.49.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.49.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.49.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.49.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.49.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.49.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
- "model.layers.49.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.49.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.49.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.49.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.49.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.49.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.49.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.49.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.49.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.49.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.49.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.49.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.49.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.49.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.49.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors",
- "model.layers.5.mlp.down_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.5.mlp.down_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.5.mlp.up_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.5.mlp.up_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
- "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.50.input_layernorm.weight": "model-00006-of-00007.safetensors",
- "model.layers.50.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.50.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.50.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.50.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.50.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.50.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.50.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.50.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.50.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
- "model.layers.50.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.50.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.50.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.50.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.50.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.50.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.50.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.50.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
- "model.layers.50.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
- "model.layers.50.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
- "model.layers.50.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
- "model.layers.50.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.50.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.50.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.50.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.51.input_layernorm.weight": "model-00006-of-00007.safetensors",
- "model.layers.51.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.51.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.51.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.51.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.51.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.51.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.51.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.51.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.51.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.51.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
- "model.layers.51.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.51.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.51.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.51.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.51.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.51.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.51.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.51.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.51.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.51.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.51.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.51.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.52.input_layernorm.weight": "model-00006-of-00007.safetensors",
- "model.layers.52.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.52.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.52.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.52.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.52.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.52.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.52.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.52.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.52.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.52.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
- "model.layers.52.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.52.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.52.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.52.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.52.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.52.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.52.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.52.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.52.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.52.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.52.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.52.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.52.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.52.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.52.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.53.input_layernorm.weight": "model-00006-of-00007.safetensors",
- "model.layers.53.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.53.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.53.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.53.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.53.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.53.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.53.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.53.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.53.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.53.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
- "model.layers.53.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.53.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.53.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.53.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.53.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.53.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.53.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.53.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.53.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.53.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.53.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.53.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.53.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.53.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.53.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.54.input_layernorm.weight": "model-00006-of-00007.safetensors",
- "model.layers.54.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.54.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.54.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.54.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.54.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.54.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.54.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.54.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.54.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.54.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
- "model.layers.54.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.54.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.54.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.54.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.54.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.54.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.54.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.54.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.54.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.54.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.54.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.54.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.54.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.54.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.54.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.55.input_layernorm.weight": "model-00006-of-00007.safetensors",
- "model.layers.55.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.55.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.55.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.55.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.55.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.55.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.55.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.55.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.55.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.55.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
- "model.layers.55.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.55.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.55.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.55.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.55.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.55.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.55.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.55.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.55.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.55.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.55.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.55.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.55.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.55.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.55.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.56.input_layernorm.weight": "model-00006-of-00007.safetensors",
- "model.layers.56.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.56.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.56.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.56.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.56.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.56.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.56.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.56.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.56.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.56.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
- "model.layers.56.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.56.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.56.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.56.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.56.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.56.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.56.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.56.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.56.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.56.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.56.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.56.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.56.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.56.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.56.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.57.input_layernorm.weight": "model-00006-of-00007.safetensors",
- "model.layers.57.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.57.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.57.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.57.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.57.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.57.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.57.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.57.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.57.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.57.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
- "model.layers.57.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.57.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.57.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.57.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.57.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.57.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.57.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.57.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.57.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.57.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.57.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.57.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.57.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.57.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.57.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.58.input_layernorm.weight": "model-00006-of-00007.safetensors",
- "model.layers.58.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.58.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.58.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.58.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.58.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.58.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.58.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.58.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.58.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.58.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
- "model.layers.58.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.58.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.58.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.58.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.58.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.58.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.58.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.58.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.58.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.58.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.58.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.58.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.58.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.58.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.58.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.59.input_layernorm.weight": "model-00006-of-00007.safetensors",
- "model.layers.59.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.59.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.59.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.59.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.59.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.59.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.59.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.59.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.59.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.59.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
- "model.layers.59.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.59.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.59.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.59.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.59.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.59.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.59.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.59.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.59.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.59.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.59.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.59.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.59.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.59.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.59.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors",
- "model.layers.6.mlp.down_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.6.mlp.down_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.6.mlp.up_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.6.mlp.up_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
- "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.60.input_layernorm.weight": "model-00007-of-00007.safetensors",
- "model.layers.60.mlp.down_proj.biases": "model-00007-of-00007.safetensors",
- "model.layers.60.mlp.down_proj.scales": "model-00007-of-00007.safetensors",
- "model.layers.60.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
- "model.layers.60.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.60.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.60.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.60.mlp.up_proj.biases": "model-00007-of-00007.safetensors",
- "model.layers.60.mlp.up_proj.scales": "model-00007-of-00007.safetensors",
- "model.layers.60.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
- "model.layers.60.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
- "model.layers.60.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.60.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.60.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.60.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.60.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.60.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.60.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.60.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.60.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.60.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.60.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.60.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
- "model.layers.60.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
- "model.layers.60.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
- "model.layers.60.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
- "model.layers.61.input_layernorm.weight": "model-00007-of-00007.safetensors",
- "model.layers.61.mlp.down_proj.biases": "model-00007-of-00007.safetensors",
- "model.layers.61.mlp.down_proj.scales": "model-00007-of-00007.safetensors",
- "model.layers.61.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
- "model.layers.61.mlp.gate_proj.biases": "model-00007-of-00007.safetensors",
- "model.layers.61.mlp.gate_proj.scales": "model-00007-of-00007.safetensors",
- "model.layers.61.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
- "model.layers.61.mlp.up_proj.biases": "model-00007-of-00007.safetensors",
- "model.layers.61.mlp.up_proj.scales": "model-00007-of-00007.safetensors",
- "model.layers.61.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
- "model.layers.61.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
- "model.layers.61.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
- "model.layers.61.self_attn.k_proj.biases": "model-00007-of-00007.safetensors",
- "model.layers.61.self_attn.k_proj.scales": "model-00007-of-00007.safetensors",
- "model.layers.61.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
- "model.layers.61.self_attn.o_proj.biases": "model-00007-of-00007.safetensors",
- "model.layers.61.self_attn.o_proj.scales": "model-00007-of-00007.safetensors",
- "model.layers.61.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
- "model.layers.61.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
- "model.layers.61.self_attn.q_proj.biases": "model-00007-of-00007.safetensors",
- "model.layers.61.self_attn.q_proj.scales": "model-00007-of-00007.safetensors",
- "model.layers.61.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
- "model.layers.61.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
- "model.layers.61.self_attn.v_proj.biases": "model-00007-of-00007.safetensors",
- "model.layers.61.self_attn.v_proj.scales": "model-00007-of-00007.safetensors",
- "model.layers.61.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
- "model.layers.62.input_layernorm.weight": "model-00007-of-00007.safetensors",
- "model.layers.62.mlp.down_proj.biases": "model-00007-of-00007.safetensors",
- "model.layers.62.mlp.down_proj.scales": "model-00007-of-00007.safetensors",
- "model.layers.62.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
- "model.layers.62.mlp.gate_proj.biases": "model-00007-of-00007.safetensors",
- "model.layers.62.mlp.gate_proj.scales": "model-00007-of-00007.safetensors",
- "model.layers.62.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
- "model.layers.62.mlp.up_proj.biases": "model-00007-of-00007.safetensors",
- "model.layers.62.mlp.up_proj.scales": "model-00007-of-00007.safetensors",
- "model.layers.62.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
- "model.layers.62.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
- "model.layers.62.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
- "model.layers.62.self_attn.k_proj.biases": "model-00007-of-00007.safetensors",
- "model.layers.62.self_attn.k_proj.scales": "model-00007-of-00007.safetensors",
- "model.layers.62.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
- "model.layers.62.self_attn.o_proj.biases": "model-00007-of-00007.safetensors",
- "model.layers.62.self_attn.o_proj.scales": "model-00007-of-00007.safetensors",
- "model.layers.62.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
- "model.layers.62.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
- "model.layers.62.self_attn.q_proj.biases": "model-00007-of-00007.safetensors",
- "model.layers.62.self_attn.q_proj.scales": "model-00007-of-00007.safetensors",
- "model.layers.62.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
- "model.layers.62.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
- "model.layers.62.self_attn.v_proj.biases": "model-00007-of-00007.safetensors",
- "model.layers.62.self_attn.v_proj.scales": "model-00007-of-00007.safetensors",
- "model.layers.62.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
- "model.layers.63.input_layernorm.weight": "model-00007-of-00007.safetensors",
- "model.layers.63.mlp.down_proj.biases": "model-00007-of-00007.safetensors",
- "model.layers.63.mlp.down_proj.scales": "model-00007-of-00007.safetensors",
- "model.layers.63.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
- "model.layers.63.mlp.gate_proj.biases": "model-00007-of-00007.safetensors",
- "model.layers.63.mlp.gate_proj.scales": "model-00007-of-00007.safetensors",
- "model.layers.63.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
- "model.layers.63.mlp.up_proj.biases": "model-00007-of-00007.safetensors",
- "model.layers.63.mlp.up_proj.scales": "model-00007-of-00007.safetensors",
- "model.layers.63.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
- "model.layers.63.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
- "model.layers.63.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
- "model.layers.63.self_attn.k_proj.biases": "model-00007-of-00007.safetensors",
- "model.layers.63.self_attn.k_proj.scales": "model-00007-of-00007.safetensors",
- "model.layers.63.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
- "model.layers.63.self_attn.o_proj.biases": "model-00007-of-00007.safetensors",
- "model.layers.63.self_attn.o_proj.scales": "model-00007-of-00007.safetensors",
- "model.layers.63.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
- "model.layers.63.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
- "model.layers.63.self_attn.q_proj.biases": "model-00007-of-00007.safetensors",
- "model.layers.63.self_attn.q_proj.scales": "model-00007-of-00007.safetensors",
- "model.layers.63.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
- "model.layers.63.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
- "model.layers.63.self_attn.v_proj.biases": "model-00007-of-00007.safetensors",
- "model.layers.63.self_attn.v_proj.scales": "model-00007-of-00007.safetensors",
- "model.layers.63.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
- "model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors",
- "model.layers.7.mlp.down_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.7.mlp.down_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.7.mlp.up_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.7.mlp.up_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
- "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
- "model.layers.8.mlp.down_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.8.mlp.down_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.8.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.8.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
- "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
- "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00007.safetensors",
- "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00007.safetensors",
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
- "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
- "model.layers.9.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.9.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.9.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.9.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.9.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.9.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
- "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.9.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.9.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.9.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.9.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.9.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.9.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
- "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
- "model.layers.9.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
- "model.layers.9.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
- "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
- "model.norm.weight": "model-00007-of-00007.safetensors"
- }
-}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B-8bit/special_tokens_map.json
deleted file mode 100644
index 1d385d62cf08bca35254547902b792c243656ec1..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-8bit/special_tokens_map.json
+++ /dev/null
@@ -1,23 +0,0 @@
-{
- "bos_token": {
- "content": "<｜begin▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- },
- "eos_token": {
- "content": "<｜end▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- },
- "pad_token": {
- "content": "<｜end▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- }
-}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B-8bit/tokenizer.json
deleted file mode 100644
index 1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-8bit/tokenizer.json
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
-size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B-8bit/tokenizer_config.json
deleted file mode 100644
index ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-8bit/tokenizer_config.json
+++ /dev/null
@@ -1,195 +0,0 @@
-{
- "add_bos_token": true,
- "add_eos_token": false,
- "add_prefix_space": null,
- "added_tokens_decoder": {
- "151643": {
- "content": "<｜end▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151644": {
- "content": "<｜User｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151645": {
- "content": "<｜Assistant｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151646": {
- "content": "<｜begin▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151647": {
- "content": "<|EOT|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151648": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151649": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151650": {
- "content": "<|quad_start|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151651": {
- "content": "<|quad_end|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151652": {
- "content": "<|vision_start|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151653": {
- "content": "<|vision_end|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151654": {
- "content": "<|vision_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151655": {
- "content": "<|image_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151656": {
- "content": "<|video_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151657": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151658": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151659": {
- "content": "<|fim_prefix|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151660": {
- "content": "<|fim_middle|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151661": {
- "content": "<|fim_suffix|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151662": {
- "content": "<|fim_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151663": {
- "content": "<|repo_name|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151664": {
- "content": "<|file_sep|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- }
- },
- "bos_token": "<｜begin▁of▁sentence｜>",
- "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
- "clean_up_tokenization_spaces": false,
- "eos_token": "<｜end▁of▁sentence｜>",
- "extra_special_tokens": {},
- "legacy": true,
- "model_max_length": 16384,
- "pad_token": "<｜end▁of▁sentence｜>",
- "sp_model_kwargs": {},
- "tokenizer_class": "LlamaTokenizerFast",
- "unk_token": null,
- "use_default_system_prompt": false
-}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/special_tokens_map.json
deleted file mode 100644
index 1d385d62cf08bca35254547902b792c243656ec1..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/special_tokens_map.json
+++ /dev/null
@@ -1,23 +0,0 @@
-{
- "bos_token": {
- "content": "<｜begin▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- },
- "eos_token": {
- "content": "<｜end▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- },
- "pad_token": {
- "content": "<｜end▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- }
-}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/tokenizer.json
deleted file mode 100644
index 1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/tokenizer.json
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
-size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/tokenizer_config.json
deleted file mode 100644
index ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/tokenizer_config.json
+++ /dev/null
@@ -1,195 +0,0 @@
-{
- "add_bos_token": true,
- "add_eos_token": false,
- "add_prefix_space": null,
- "added_tokens_decoder": {
- "151643": {
- "content": "<｜end▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151644": {
- "content": "<｜User｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151645": {
- "content": "<｜Assistant｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151646": {
- "content": "<｜begin▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151647": {
- "content": "<|EOT|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151648": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151649": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151650": {
- "content": "<|quad_start|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151651": {
- "content": "<|quad_end|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151652": {
- "content": "<|vision_start|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151653": {
- "content": "<|vision_end|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151654": {
- "content": "<|vision_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151655": {
- "content": "<|image_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151656": {
- "content": "<|video_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151657": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151658": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151659": {
- "content": "<|fim_prefix|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151660": {
- "content": "<|fim_middle|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151661": {
- "content": "<|fim_suffix|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151662": {
- "content": "<|fim_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151663": {
- "content": "<|repo_name|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151664": {
- "content": "<|file_sep|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- }
- },
- "bos_token": "<｜begin▁of▁sentence｜>",
- "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
- "clean_up_tokenization_spaces": false,
- "eos_token": "<｜end▁of▁sentence｜>",
- "extra_special_tokens": {},
- "legacy": true,
- "model_max_length": 16384,
- "pad_token": "<｜end▁of▁sentence｜>",
- "sp_model_kwargs": {},
- "tokenizer_class": "LlamaTokenizerFast",
- "unk_token": null,
- "use_default_system_prompt": false
-}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/config.json b/DeepSeek-R1-Distill-Qwen-32B-float16/config.json
deleted file mode 100644
index e95cadc68ad8595dd9b2c7a5e90ab983db75aa35..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-float16/config.json
+++ /dev/null
@@ -1,27 +0,0 @@
-{
- "architectures": [
- "Qwen2ForCausalLM"
- ],
- "attention_dropout": 0.0,
- "bos_token_id": 151643,
- "eos_token_id": 151643,
- "hidden_act": "silu",
- "hidden_size": 5120,
- "initializer_range": 0.02,
- "intermediate_size": 27648,
- "max_position_embeddings": 131072,
- "max_window_layers": 64,
- "model_type": "qwen2",
- "num_attention_heads": 40,
- "num_hidden_layers": 64,
- "num_key_value_heads": 8,
- "rms_norm_eps": 1e-05,
- "rope_theta": 1000000.0,
- "sliding_window": 131072,
- "tie_word_embeddings": false,
- "torch_dtype": "bfloat16",
- "transformers_version": "4.43.1",
- "use_cache": true,
- "use_sliding_window": false,
- "vocab_size": 152064
-}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00001-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00001-of-00013.safetensors
deleted file mode 100644
index f9b3148217f6edfcf6a391ba995b3e52f50d403b..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00001-of-00013.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:afb60b214aeb4520856843c603633d95b689a51e4971ad96f35c9d2cdb42bf1c
-size 5174846564
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00002-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00002-of-00013.safetensors
deleted file mode 100644
index f631c32ffe6f060c7f63793770bf6358c8056378..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00002-of-00013.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:027fb274298705462adc75c960a642ffc9e57f7586964e27a90a86bc45e60448
-size 5285039836
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00003-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00003-of-00013.safetensors
deleted file mode 100644
index 96c45e355e96e9246cb8d7228d2b9e03b635fc6c..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00003-of-00013.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:813f934d39fe60e38accf811cea82e8540ee22fb7e2635773b27214e483ae4fa
-size 5159174970
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00004-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00004-of-00013.safetensors
deleted file mode 100644
index dea4e3abacb4cd9b0f09f6b65d3b77bd1f7f840b..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00004-of-00013.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8c60fef930ed0ddcf916b4e69c2aae742359f559a5c07d8cdb5e0f0ad3514c39
-size 5159174991
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00005-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00005-of-00013.safetensors
deleted file mode 100644
index 4175cb52fe8f7c101a221a8188babf56b91077c3..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00005-of-00013.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:228db8858bc8ec58a20c8f168d9bd3034de0ebd135752f41d8f035676f7a337d
-size 5285039914
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00006-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00006-of-00013.safetensors
deleted file mode 100644
index 71757ae754ad2d3e6accaaa5f5770a75fe98f77b..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00006-of-00013.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:606c8f7528115f78b318c4836f5ac17da26509c7bee422933a1ceee2621a20e8
-size 5159174989
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00007-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00007-of-00013.safetensors
deleted file mode 100644
index 7e6e77ad5d27f111880f93820572681d115287d8..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00007-of-00013.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:14a326ed0bd21631aeace8bfdb14f17c24b18e623fb3d0e5834be005c203e54d
-size 5159174993
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00008-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00008-of-00013.safetensors
deleted file mode 100644
index adf23b2da84529dfa8e0f5b3a7755520c18d9d2e..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00008-of-00013.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:763a486bedfa701f0a2f290ee67da5e75c87ec8ca1a9816fc4b11f9e4b5d0741
-size 5285039914
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00009-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00009-of-00013.safetensors
deleted file mode 100644
index 83f524ef62fa21a016cb6f708247ab15b8424819..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00009-of-00013.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c14d13b82b1f32caef91d77ea2569d2c48093961837b5a36be1a8139444e3241
-size 5159174987
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00010-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00010-of-00013.safetensors
deleted file mode 100644
index 9e285fc95b5f97f3abc326908eb810b527552dda..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00010-of-00013.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7f1ae29c430768d0fd4f24f9a6cfe9b05bac9c1f3a73f8303c8cafc55d57ad2f
-size 5159174997
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00011-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00011-of-00013.safetensors
deleted file mode 100644
index 8aa8b7e80034b4c4d424012cd919ea9321dd459c..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00011-of-00013.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0661b1670ecb41c0f4b8851400745ea38c347b0e0de6735ef473e00e3116d811
-size 5285039932
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00012-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00012-of-00013.safetensors
deleted file mode 100644
index 3ef96b9f4e5a5371827f409412725275f8acc986..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00012-of-00013.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:07297b2d73eea88a5bd74f847fa705b236d5a1545f90b7917580a4debf582c81
-size 5159174991
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00013-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00013-of-00013.safetensors
deleted file mode 100644
index 90456dc98939515c4c6dbd9b8c70a715bcd20521..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00013-of-00013.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:54a0b5e489b6ced01166836c08cfd5b90957ea540628ac9d4534b2d084b00c46
-size 3098609663
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B-float16/model.safetensors.index.json
deleted file mode 100644
index 6b47c65cee2a02155e504beb592a01f9bfdec153..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-float16/model.safetensors.index.json
+++ /dev/null
@@ -1,778 +0,0 @@
-{
- "metadata": {
- "total_size": 65527752704
- },
- "weight_map": {
- "lm_head.weight": "model-00013-of-00013.safetensors",
- "model.embed_tokens.weight": "model-00001-of-00013.safetensors",
- "model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors",
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
- "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors",
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
- "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.10.input_layernorm.weight": "model-00003-of-00013.safetensors",
- "model.layers.10.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.10.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
- "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
- "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
- "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
- "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.11.input_layernorm.weight": "model-00003-of-00013.safetensors",
- "model.layers.11.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.11.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
- "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
- "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
- "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
- "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.12.input_layernorm.weight": "model-00003-of-00013.safetensors",
- "model.layers.12.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.12.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
- "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
- "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
- "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
- "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.13.input_layernorm.weight": "model-00003-of-00013.safetensors",
- "model.layers.13.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.13.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
- "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
- "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
- "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
- "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.14.input_layernorm.weight": "model-00004-of-00013.safetensors",
- "model.layers.14.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.14.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
- "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
- "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
- "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
- "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.15.input_layernorm.weight": "model-00004-of-00013.safetensors",
- "model.layers.15.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.15.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
- "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
- "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
- "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
- "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.16.input_layernorm.weight": "model-00004-of-00013.safetensors",
- "model.layers.16.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.16.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
- "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
- "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
- "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
- "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.17.input_layernorm.weight": "model-00004-of-00013.safetensors",
- "model.layers.17.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.17.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
- "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
- "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
- "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
- "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.18.input_layernorm.weight": "model-00004-of-00013.safetensors",
- "model.layers.18.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.18.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
- "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
- "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
- "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
- "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.19.input_layernorm.weight": "model-00005-of-00013.safetensors",
- "model.layers.19.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.19.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
- "model.layers.19.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
- "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.19.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
- "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.19.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
- "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
- "model.layers.2.input_layernorm.weight": "model-00001-of-00013.safetensors",
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
- "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.20.input_layernorm.weight": "model-00005-of-00013.safetensors",
- "model.layers.20.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.20.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
- "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
- "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
- "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
- "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.21.input_layernorm.weight": "model-00005-of-00013.safetensors",
- "model.layers.21.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.21.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
- "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
- "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
- "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
- "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.22.input_layernorm.weight": "model-00005-of-00013.safetensors",
- "model.layers.22.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.22.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
- "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
- "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
- "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
- "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.23.input_layernorm.weight": "model-00005-of-00013.safetensors",
- "model.layers.23.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.23.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
- "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
- "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
- "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
- "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.24.input_layernorm.weight": "model-00005-of-00013.safetensors",
- "model.layers.24.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.24.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
- "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
- "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
- "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
- "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.25.input_layernorm.weight": "model-00006-of-00013.safetensors",
- "model.layers.25.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.25.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
- "model.layers.25.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
- "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.25.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
- "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.25.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
- "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
- "model.layers.26.input_layernorm.weight": "model-00006-of-00013.safetensors",
- "model.layers.26.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.26.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
- "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
- "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
- "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
- "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.27.input_layernorm.weight": "model-00006-of-00013.safetensors",
- "model.layers.27.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.27.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
- "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
- "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
- "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
- "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.28.input_layernorm.weight": "model-00006-of-00013.safetensors",
- "model.layers.28.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.28.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
- "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
- "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
- "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
- "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.29.input_layernorm.weight": "model-00006-of-00013.safetensors",
- "model.layers.29.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.29.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
- "model.layers.29.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
- "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.29.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
- "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.29.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
- "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors",
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.3.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
- "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
- "model.layers.30.input_layernorm.weight": "model-00007-of-00013.safetensors",
- "model.layers.30.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.30.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
- "model.layers.30.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
- "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.30.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
- "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.30.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
- "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
- "model.layers.31.input_layernorm.weight": "model-00007-of-00013.safetensors",
- "model.layers.31.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.31.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
- "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
- "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
- "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
- "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.32.input_layernorm.weight": "model-00007-of-00013.safetensors",
- "model.layers.32.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.32.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
- "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
- "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
- "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
- "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.33.input_layernorm.weight": "model-00007-of-00013.safetensors",
- "model.layers.33.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.33.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
- "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
- "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
- "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
- "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.34.input_layernorm.weight": "model-00007-of-00013.safetensors",
- "model.layers.34.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.34.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
- "model.layers.34.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
- "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.34.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
- "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.34.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
- "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.35.input_layernorm.weight": "model-00008-of-00013.safetensors",
- "model.layers.35.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.35.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
- "model.layers.35.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
- "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.35.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
- "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.35.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
- "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
- "model.layers.36.input_layernorm.weight": "model-00008-of-00013.safetensors",
- "model.layers.36.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.36.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
- "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
- "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
- "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
- "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.37.input_layernorm.weight": "model-00008-of-00013.safetensors",
- "model.layers.37.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.37.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
- "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
- "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
- "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
- "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.38.input_layernorm.weight": "model-00008-of-00013.safetensors",
- "model.layers.38.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.38.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
- "model.layers.38.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
- "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.38.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
- "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.38.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
- "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.39.input_layernorm.weight": "model-00008-of-00013.safetensors",
- "model.layers.39.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.39.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.39.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
- "model.layers.39.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
- "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.39.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
- "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.39.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
- "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.4.input_layernorm.weight": "model-00002-of-00013.safetensors",
- "model.layers.4.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.4.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
- "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
- "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
- "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
- "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.40.input_layernorm.weight": "model-00008-of-00013.safetensors",
- "model.layers.40.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.40.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.40.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
- "model.layers.40.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
- "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.40.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
- "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.40.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
- "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.41.input_layernorm.weight": "model-00009-of-00013.safetensors",
- "model.layers.41.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.41.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
- "model.layers.41.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
- "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.41.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
- "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.41.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
- "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
- "model.layers.42.input_layernorm.weight": "model-00009-of-00013.safetensors",
- "model.layers.42.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.42.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
- "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
- "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
- "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
- "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.43.input_layernorm.weight": "model-00009-of-00013.safetensors",
- "model.layers.43.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.43.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.43.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
- "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
- "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
- "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
- "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.44.input_layernorm.weight": "model-00009-of-00013.safetensors",
- "model.layers.44.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.44.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.44.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.44.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
- "model.layers.44.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
- "model.layers.44.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.44.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.44.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
- "model.layers.44.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.44.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
- "model.layers.44.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.45.input_layernorm.weight": "model-00009-of-00013.safetensors",
- "model.layers.45.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.45.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.45.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.45.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
- "model.layers.45.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
- "model.layers.45.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.45.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.45.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
- "model.layers.45.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.45.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
- "model.layers.45.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.46.input_layernorm.weight": "model-00010-of-00013.safetensors",
- "model.layers.46.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.46.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.46.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
- "model.layers.46.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
- "model.layers.46.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.46.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.46.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
- "model.layers.46.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.46.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
- "model.layers.46.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
- "model.layers.47.input_layernorm.weight": "model-00010-of-00013.safetensors",
- "model.layers.47.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.47.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
- "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
- "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
- "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
- "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.48.input_layernorm.weight": "model-00010-of-00013.safetensors",
- "model.layers.48.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.48.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.48.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
- "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
- "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
- "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
- "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.49.input_layernorm.weight": "model-00010-of-00013.safetensors",
- "model.layers.49.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.49.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.49.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.49.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
- "model.layers.49.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
- "model.layers.49.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.49.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.49.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
- "model.layers.49.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.49.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
- "model.layers.49.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.5.input_layernorm.weight": "model-00002-of-00013.safetensors",
- "model.layers.5.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.5.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
- "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
- "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
- "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
- "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.50.input_layernorm.weight": "model-00010-of-00013.safetensors",
- "model.layers.50.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.50.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.50.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.50.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
- "model.layers.50.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
- "model.layers.50.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.50.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.50.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
- "model.layers.50.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.50.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
- "model.layers.50.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.51.input_layernorm.weight": "model-00011-of-00013.safetensors",
- "model.layers.51.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.51.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.51.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
- "model.layers.51.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
- "model.layers.51.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.51.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.51.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
- "model.layers.51.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.51.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
- "model.layers.51.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
- "model.layers.52.input_layernorm.weight": "model-00011-of-00013.safetensors",
- "model.layers.52.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.52.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
- "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
- "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
- "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
- "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.53.input_layernorm.weight": "model-00011-of-00013.safetensors",
- "model.layers.53.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.53.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.53.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
- "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
- "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
- "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
- "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.54.input_layernorm.weight": "model-00011-of-00013.safetensors",
- "model.layers.54.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.54.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.54.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.54.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
- "model.layers.54.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
- "model.layers.54.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.54.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.54.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
- "model.layers.54.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.54.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
- "model.layers.54.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.55.input_layernorm.weight": "model-00011-of-00013.safetensors",
- "model.layers.55.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.55.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.55.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.55.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
- "model.layers.55.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
- "model.layers.55.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.55.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.55.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
- "model.layers.55.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.55.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
- "model.layers.55.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.56.input_layernorm.weight": "model-00011-of-00013.safetensors",
- "model.layers.56.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.56.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.56.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.56.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
- "model.layers.56.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
- "model.layers.56.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.56.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.56.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
- "model.layers.56.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.56.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
- "model.layers.56.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.57.input_layernorm.weight": "model-00012-of-00013.safetensors",
- "model.layers.57.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.57.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
- "model.layers.57.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
- "model.layers.57.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.57.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.57.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
- "model.layers.57.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.57.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
- "model.layers.57.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
- "model.layers.58.input_layernorm.weight": "model-00012-of-00013.safetensors",
- "model.layers.58.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.58.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.58.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
- "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
- "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
- "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
- "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.59.input_layernorm.weight": "model-00012-of-00013.safetensors",
- "model.layers.59.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.59.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.59.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.59.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
- "model.layers.59.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
- "model.layers.59.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.59.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.59.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
- "model.layers.59.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.59.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
- "model.layers.59.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.6.input_layernorm.weight": "model-00002-of-00013.safetensors",
- "model.layers.6.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.6.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
- "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
- "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
- "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
- "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.60.input_layernorm.weight": "model-00012-of-00013.safetensors",
- "model.layers.60.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.60.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.60.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.60.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
- "model.layers.60.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
- "model.layers.60.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.60.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.60.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
- "model.layers.60.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.60.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
- "model.layers.60.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.61.input_layernorm.weight": "model-00012-of-00013.safetensors",
- "model.layers.61.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.61.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.61.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.61.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
- "model.layers.61.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
- "model.layers.61.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.61.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.61.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
- "model.layers.61.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.61.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
- "model.layers.61.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.62.input_layernorm.weight": "model-00013-of-00013.safetensors",
- "model.layers.62.mlp.down_proj.weight": "model-00013-of-00013.safetensors",
- "model.layers.62.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.62.mlp.up_proj.weight": "model-00013-of-00013.safetensors",
- "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00013.safetensors",
- "model.layers.62.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
- "model.layers.62.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.62.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.62.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
- "model.layers.62.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.62.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
- "model.layers.62.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
- "model.layers.63.input_layernorm.weight": "model-00013-of-00013.safetensors",
- "model.layers.63.mlp.down_proj.weight": "model-00013-of-00013.safetensors",
- "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00013.safetensors",
- "model.layers.63.mlp.up_proj.weight": "model-00013-of-00013.safetensors",
- "model.layers.63.post_attention_layernorm.weight": "model-00013-of-00013.safetensors",
- "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00013.safetensors",
- "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00013.safetensors",
- "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00013.safetensors",
- "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00013.safetensors",
- "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00013.safetensors",
- "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00013.safetensors",
- "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00013.safetensors",
- "model.layers.7.input_layernorm.weight": "model-00002-of-00013.safetensors",
- "model.layers.7.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.7.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
- "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
- "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
- "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
- "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.8.input_layernorm.weight": "model-00002-of-00013.safetensors",
- "model.layers.8.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.8.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
- "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
- "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
- "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
- "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.9.input_layernorm.weight": "model-00003-of-00013.safetensors",
- "model.layers.9.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.9.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
- "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
- "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
- "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
- "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
- "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
- "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
- "model.norm.weight": "model-00013-of-00013.safetensors"
- }
-}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B-float16/special_tokens_map.json
deleted file mode 100644
index 1d385d62cf08bca35254547902b792c243656ec1..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-float16/special_tokens_map.json
+++ /dev/null
@@ -1,23 +0,0 @@
-{
- "bos_token": {
- "content": "<｜begin▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- },
- "eos_token": {
- "content": "<｜end▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- },
- "pad_token": {
- "content": "<｜end▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- }
-}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B-float16/tokenizer.json
deleted file mode 100644
index 1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-float16/tokenizer.json
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
-size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B-float16/tokenizer_config.json
deleted file mode 100644
index ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd..0000000000000000000000000000000000000000
--- a/DeepSeek-R1-Distill-Qwen-32B-float16/tokenizer_config.json
+++ /dev/null
@@ -1,195 +0,0 @@
-{
- "add_bos_token": true,
- "add_eos_token": false,
- "add_prefix_space": null,
- "added_tokens_decoder": {
- "151643": {
- "content": "<｜end▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151644": {
- "content": "<｜User｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151645": {
- "content": "<｜Assistant｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151646": {
- "content": "<｜begin▁of▁sentence｜>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151647": {
- "content": "<|EOT|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151648": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151649": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151650": {
- "content": "<|quad_start|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151651": {
- "content": "<|quad_end|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151652": {
- "content": "<|vision_start|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151653": {
- "content": "<|vision_end|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151654": {
- "content": "<|vision_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151655": {
- "content": "<|image_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151656": {
- "content": "<|video_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "151657": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151658": {
- "content": "",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151659": {
- "content": "<|fim_prefix|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151660": {
- "content": "<|fim_middle|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151661": {
- "content": "<|fim_suffix|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151662": {
- "content": "<|fim_pad|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151663": {
- "content": "<|repo_name|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "151664": {
- "content": "<|file_sep|>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": false
- }
- },
- "bos_token": "<｜begin▁of▁sentence｜>",
- "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
- "clean_up_tokenization_spaces": false,
- "eos_token": "<｜end▁of▁sentence｜>",
- "extra_special_tokens": {},
- "legacy": true,
- "model_max_length": 16384,
- "pad_token": "<｜end▁of▁sentence｜>",
- "sp_model_kwargs": {},
- "tokenizer_class": "LlamaTokenizerFast",
- "unk_token": null,
- "use_default_system_prompt": false
-}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/config.json b/DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/config.json
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/config.json
rename to DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/config.json
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00001-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/model-00001-of-00004.safetensors
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00001-of-00004.safetensors
rename to DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/model-00001-of-00004.safetensors
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00002-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/model-00002-of-00004.safetensors
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00002-of-00004.safetensors
rename to DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/model-00002-of-00004.safetensors
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00003-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/model-00003-of-00004.safetensors
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00003-of-00004.safetensors
rename to DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/model-00003-of-00004.safetensors
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00004-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/model-00004-of-00004.safetensors
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00004-of-00004.safetensors
rename to DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/model-00004-of-00004.safetensors
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/model.safetensors.index.json
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model.safetensors.index.json
rename to DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/model.safetensors.index.json
diff --git a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/special_tokens_map.json
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/special_tokens_map.json
rename to DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/special_tokens_map.json
diff --git a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/tokenizer.json
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/tokenizer.json
rename to DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/tokenizer.json
diff --git a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/tokenizer_config.json
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/tokenizer_config.json
rename to DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/tokenizer_config.json
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/config.json b/DeepSeek-R1-Distill-Qwen-32B_4bit/config.json
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-4bit/config.json
rename to DeepSeek-R1-Distill-Qwen-32B_4bit/config.json
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/model-00001-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B_4bit/model-00001-of-00004.safetensors
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-4bit/model-00001-of-00004.safetensors
rename to DeepSeek-R1-Distill-Qwen-32B_4bit/model-00001-of-00004.safetensors
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/model-00002-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B_4bit/model-00002-of-00004.safetensors
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-4bit/model-00002-of-00004.safetensors
rename to DeepSeek-R1-Distill-Qwen-32B_4bit/model-00002-of-00004.safetensors
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/model-00003-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B_4bit/model-00003-of-00004.safetensors
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-4bit/model-00003-of-00004.safetensors
rename to DeepSeek-R1-Distill-Qwen-32B_4bit/model-00003-of-00004.safetensors
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/model-00004-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B_4bit/model-00004-of-00004.safetensors
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-4bit/model-00004-of-00004.safetensors
rename to DeepSeek-R1-Distill-Qwen-32B_4bit/model-00004-of-00004.safetensors
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B_4bit/model.safetensors.index.json
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-4bit/model.safetensors.index.json
rename to DeepSeek-R1-Distill-Qwen-32B_4bit/model.safetensors.index.json
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B_4bit/special_tokens_map.json
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/special_tokens_map.json
rename to DeepSeek-R1-Distill-Qwen-32B_4bit/special_tokens_map.json
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B_4bit/tokenizer.json
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/tokenizer.json
rename to DeepSeek-R1-Distill-Qwen-32B_4bit/tokenizer.json
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B_4bit/tokenizer_config.json
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/tokenizer_config.json
rename to DeepSeek-R1-Distill-Qwen-32B_4bit/tokenizer_config.json
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/config.json b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/config.json
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/config.json
rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/config.json
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00001-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00001-of-00013.safetensors
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00001-of-00013.safetensors
rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00001-of-00013.safetensors
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00002-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00002-of-00013.safetensors
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00002-of-00013.safetensors
rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00002-of-00013.safetensors
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00003-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00003-of-00013.safetensors
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00003-of-00013.safetensors
rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00003-of-00013.safetensors
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00004-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00004-of-00013.safetensors
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00004-of-00013.safetensors
rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00004-of-00013.safetensors
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00005-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00005-of-00013.safetensors
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00005-of-00013.safetensors
rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00005-of-00013.safetensors
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00006-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00006-of-00013.safetensors
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00006-of-00013.safetensors
rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00006-of-00013.safetensors
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00007-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00007-of-00013.safetensors
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00007-of-00013.safetensors
rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00007-of-00013.safetensors
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00008-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00008-of-00013.safetensors
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00008-of-00013.safetensors
rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00008-of-00013.safetensors
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00009-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00009-of-00013.safetensors
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00009-of-00013.safetensors
rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00009-of-00013.safetensors
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00010-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00010-of-00013.safetensors
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00010-of-00013.safetensors
rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00010-of-00013.safetensors
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00011-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00011-of-00013.safetensors
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00011-of-00013.safetensors
rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00011-of-00013.safetensors
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00012-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00012-of-00013.safetensors
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00012-of-00013.safetensors
rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00012-of-00013.safetensors
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00013-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00013-of-00013.safetensors
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00013-of-00013.safetensors
rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00013-of-00013.safetensors
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model.safetensors.index.json
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model.safetensors.index.json
rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model.safetensors.index.json
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/special_tokens_map.json
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/special_tokens_map.json
rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/special_tokens_map.json
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/tokenizer.json
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/tokenizer.json
rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/tokenizer.json
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/tokenizer_config.json
similarity index 100%
rename from DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/tokenizer_config.json
rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/tokenizer_config.json
diff --git a/LICENSE b/LICENSE
deleted file mode 100644
index d42fae903e9fa07f3e8edb0db00a8d905ba49560..0000000000000000000000000000000000000000
--- a/LICENSE
+++ /dev/null
@@ -1,21 +0,0 @@
-MIT License
-
-Copyright (c) 2023 DeepSeek
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
\ No newline at end of file
diff --git a/README.md b/README.md
deleted file mode 100644
index 8c87f6c865632c1f3eb5107c43f927f3934303a8..0000000000000000000000000000000000000000
--- a/README.md
+++ /dev/null
@@ -1,68 +0,0 @@
----
-quantized_by: sealad886
-license_link: https://huggingface.co./deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/blob/main/LICENSE
-language:
-- en
-pipeline_tag: text-generation
-base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
-tags:
-- chat
-- mlx
-- conversations
----
-
-# mlx-community/DeepSeek-R1-Distill-Qwen-32B
-
-This Model [mlx-community/DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co./mlx-community/DeepSeek-R1-Distill-Qwen-32B) contains multiple quantized variants of the base model [deepseek-ai/DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co./deepseek-ai/DeepSeek-R1-Distill-Qwen-32B). The model was converted to MLX format using mlx-lm version 0.21.5.
-
-The conversion process applied different quantization strategies to produce variants that offer trade-offs between memory footprint, inference speed, and accuracy. In addition to the default 4-bit conversion, you will find both uniform and mixed quantized files at various bit widths (2-bit, 3-bit, 6-bit, and 8-bit). This multi-quantized approach allows users to select the best variant for their deployment scenario, balancing precision and performance.
-
-## Quantization Configurations
-
-The model conversion uses a range of quantization configurations defined via `mlx_lm.convert`. These configurations fall into three main categories:
-
-1. **Uniform Quantization:**
- Applies the same bit width to all layers.
- - **3bit:** Uniform 3-bit quantization.
- - **4bit:** Uniform 4-bit quantization (default).
- - **6bit:** Uniform 6-bit quantization.
- - **8bit:** Uniform 8-bit quantization.
-
-2. **Mixed Quantization:**
- Uses a custom predicate function to decide the bit width for each layer—allowing different layers to use different precisions.
- - **2,6_mixed:** Uses the `mixed_2_6` predicate to choose between 2-bit and 6-bit quantization.
- - **3,6_mixed:** Uses the `mixed_3_6` predicate to choose between 3-bit and 6-bit quantization.
- - **3,4_mixed:** Built via `mixed_quant_predicate_builder(3, 4, group_size)`, it mixes 3-bit and 4-bit precision.
- - **4,6_mixed:** Built via `mixed_quant_predicate_builder(4, 6, group_size)`, it mixes 4-bit and 6-bit precision.
- - **4,8_mixed:** Built via `mixed_quant_predicate_builder(4, 8, group_size)`, it mixes 4-bit and 8-bit precision.
-
- Where `group_size = 64` (which is default for other quantization methods).
-
-3. **Non-Quantized Conversions:**
- Converts the model to a different floating point precision without quantizing weights.
- - **bfloat16:** Model converted to bfloat16 precision.
- - **float16:** Model converted to float16 precision.
-
-## Use with mlx
-
-Install the MLX library:
-```bash
-pip install mlx-lm
-```
-
-Load the model and generate text:
-```python
-from mlx_lm import load, generate
-
-model, tokenizer = load("mlx-community/DeepSeek-R1-Distill-Qwen-32B-MLX")
-
-prompt = "hello"
-
-if tokenizer.chat_template is not None:
- messages = [{"role": "user", "content": prompt}]
- prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
-
-response = generate(model, tokenizer, prompt=prompt, verbose=True)
-```
-
-Each configuration is optimized to meet specific requirements, enabling a forward-thinking approach in model deployment where resource constraints and performance targets are key considerations.
\ No newline at end of file