Upload folder using huggingface_hub

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3676fdedea6525b5ae18d979e1e5342003fce3322cebe32422cb8b922f620ea9
-size 4938989417
+oid sha256:f444f466b42e06ad78e9c690b730fec321c55a404791f81f0c918a644cf35e58
+size 4938987913

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34d9ca5cdd7da30823b1ae55482da557452d9436c8236795503f8d5af4034567
-size 4947394872
+oid sha256:c89e17b1f9c5a181922f8802f380452e5609ac99ea526a3d07f9bebb3b0f31ac
+size 4947393368

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6220e823c19258d8899e70040fccd203d62ab6250e8415f457f724a2fdb2c51
-size 3590491472
+oid sha256:8f3ef429c06eb0360ba1e166f0dafa9d9a5b959896bbdb1d4881d1bad4517c33
+size 3590490472

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 13476831489
+    "total_size": 13476831425
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",
@@ -16,7 +16,6 @@
     "model.layers.0.self_attn.kv_scale": "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.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.v_proj.output_quantizer._amax": "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.weight": "model-00001-of-00003.safetensors",
@@ -28,7 +27,6 @@
     "model.layers.1.self_attn.kv_scale": "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.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.v_proj.output_quantizer._amax": "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.weight": "model-00001-of-00003.safetensors",
@@ -40,7 +38,6 @@
     "model.layers.10.self_attn.kv_scale": "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.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.v_proj.output_quantizer._amax": "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-00002-of-00003.safetensors",
     "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
@@ -52,7 +49,6 @@
     "model.layers.11.self_attn.kv_scale": "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.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.self_attn.v_proj.output_quantizer._amax": "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-00002-of-00003.safetensors",
     "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
@@ -64,7 +60,6 @@
     "model.layers.12.self_attn.kv_scale": "model-00002-of-00003.safetensors",
     "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.v_proj.output_quantizer._amax": "model-00002-of-00003.safetensors",
     "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
@@ -76,7 +71,6 @@
     "model.layers.13.self_attn.kv_scale": "model-00002-of-00003.safetensors",
     "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.v_proj.output_quantizer._amax": "model-00002-of-00003.safetensors",
     "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
@@ -88,7 +82,6 @@
     "model.layers.14.self_attn.kv_scale": "model-00002-of-00003.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.v_proj.output_quantizer._amax": "model-00002-of-00003.safetensors",
     "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
@@ -100,7 +93,6 @@
     "model.layers.15.self_attn.kv_scale": "model-00002-of-00003.safetensors",
     "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.v_proj.output_quantizer._amax": "model-00002-of-00003.safetensors",
     "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
@@ -112,7 +104,6 @@
     "model.layers.16.self_attn.kv_scale": "model-00002-of-00003.safetensors",
     "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.v_proj.output_quantizer._amax": "model-00002-of-00003.safetensors",
     "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
@@ -124,7 +115,6 @@
     "model.layers.17.self_attn.kv_scale": "model-00002-of-00003.safetensors",
     "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.v_proj.output_quantizer._amax": "model-00002-of-00003.safetensors",
     "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
@@ -136,7 +126,6 @@
     "model.layers.18.self_attn.kv_scale": "model-00002-of-00003.safetensors",
     "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.v_proj.output_quantizer._amax": "model-00002-of-00003.safetensors",
     "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
@@ -148,7 +137,6 @@
     "model.layers.19.self_attn.kv_scale": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.v_proj.output_quantizer._amax": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
@@ -160,7 +148,6 @@
     "model.layers.2.self_attn.kv_scale": "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.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.v_proj.output_quantizer._amax": "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-00002-of-00003.safetensors",
     "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
@@ -172,7 +159,6 @@
     "model.layers.20.self_attn.kv_scale": "model-00002-of-00003.safetensors",
     "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.v_proj.output_quantizer._amax": "model-00002-of-00003.safetensors",
     "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
@@ -184,7 +170,6 @@
     "model.layers.21.self_attn.kv_scale": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.v_proj.output_quantizer._amax": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
@@ -196,7 +181,6 @@
     "model.layers.22.self_attn.kv_scale": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.v_proj.output_quantizer._amax": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
@@ -208,7 +192,6 @@
     "model.layers.23.self_attn.kv_scale": "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.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.v_proj.output_quantizer._amax": "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-00003-of-00003.safetensors",
     "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
@@ -220,7 +203,6 @@
     "model.layers.24.self_attn.kv_scale": "model-00003-of-00003.safetensors",
     "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.v_proj.output_quantizer._amax": "model-00003-of-00003.safetensors",
     "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
@@ -232,7 +214,6 @@
     "model.layers.25.self_attn.kv_scale": "model-00003-of-00003.safetensors",
     "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.v_proj.output_quantizer._amax": "model-00003-of-00003.safetensors",
     "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
@@ -244,7 +225,6 @@
     "model.layers.26.self_attn.kv_scale": "model-00003-of-00003.safetensors",
     "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.v_proj.output_quantizer._amax": "model-00003-of-00003.safetensors",
     "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
@@ -256,7 +236,6 @@
     "model.layers.27.self_attn.kv_scale": "model-00003-of-00003.safetensors",
     "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.v_proj.output_quantizer._amax": "model-00003-of-00003.safetensors",
     "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
@@ -268,7 +247,6 @@
     "model.layers.28.self_attn.kv_scale": "model-00003-of-00003.safetensors",
     "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.v_proj.output_quantizer._amax": "model-00003-of-00003.safetensors",
     "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
@@ -280,7 +258,6 @@
     "model.layers.29.self_attn.kv_scale": "model-00003-of-00003.safetensors",
     "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.v_proj.output_quantizer._amax": "model-00003-of-00003.safetensors",
     "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
@@ -292,7 +269,6 @@
     "model.layers.3.self_attn.kv_scale": "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.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.v_proj.output_quantizer._amax": "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-00003-of-00003.safetensors",
     "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
@@ -304,7 +280,6 @@
     "model.layers.30.self_attn.kv_scale": "model-00003-of-00003.safetensors",
     "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.v_proj.output_quantizer._amax": "model-00003-of-00003.safetensors",
     "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
@@ -316,7 +291,6 @@
     "model.layers.31.self_attn.kv_scale": "model-00003-of-00003.safetensors",
     "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.v_proj.output_quantizer._amax": "model-00003-of-00003.safetensors",
     "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
@@ -328,7 +302,6 @@
     "model.layers.4.self_attn.kv_scale": "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.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.v_proj.output_quantizer._amax": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
@@ -340,7 +313,6 @@
     "model.layers.5.self_attn.kv_scale": "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.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.v_proj.output_quantizer._amax": "model-00001-of-00003.safetensors",
     "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
@@ -352,7 +324,6 @@
     "model.layers.6.self_attn.kv_scale": "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.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.v_proj.output_quantizer._amax": "model-00001-of-00003.safetensors",
     "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
@@ -364,7 +335,6 @@
     "model.layers.7.self_attn.kv_scale": "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.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.v_proj.output_quantizer._amax": "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.weight": "model-00001-of-00003.safetensors",
@@ -376,7 +346,6 @@
     "model.layers.8.self_attn.kv_scale": "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.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.v_proj.output_quantizer._amax": "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.weight": "model-00001-of-00003.safetensors",
@@ -388,7 +357,6 @@
     "model.layers.9.self_attn.kv_scale": "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.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.v_proj.output_quantizer._amax": "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"
   }