Upload LlamaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "fsaudm/Meta-Llama-3.1-8B-Instruct-INT4",
+  "_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -25,11 +25,11 @@
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_storage": "uint8",
-    "bnb_4bit_quant_type": "fp4",
-    "bnb_4bit_use_double_quant": false,
-    "llm_int8_enable_fp32_cpu_offload": false,
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": true,
     "llm_int8_has_fp16_weight": false,
     "llm_int8_skip_modules": null,
     "llm_int8_threshold": 6.0,

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:167f1d23187acb72e80bce74c54e61b7da3a25eae1c207bfc3a6a6425077cb9c
-size 4977222760
+oid sha256:3c4a79180091cae0d86a4dbb6a4ff24af3e5058c8be5930cba7e39113eebd854
+size 4651954871

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bb7a5c6402e8a0f3838d4d45f59e5f3fff4f0f6375ef5c71b2b4604cccded4c
+oid sha256:5321ca97dd0968a3e2b676b3a42728e9f5327d516bcf0addd4e9cd61c068a1ad
 size 1050673280