Upload LlamaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "meta-llama/Meta-Llama-3.1-70B-Instruct",
+  "_name_or_path": "unsloth/Meta-Llama-3.1-70B-Instruct-bnb-4bit",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -21,6 +21,7 @@
   "num_attention_heads": 64,
   "num_hidden_layers": 80,
   "num_key_value_heads": 8,
+  "pad_token_id": 128004,
   "pretraining_tp": 1,
   "quantization_config": {
     "_load_in_4bit": true,
@@ -29,7 +30,7 @@
     "bnb_4bit_quant_storage": "uint8",
     "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": true,
-    "llm_int8_enable_fp32_cpu_offload": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
     "llm_int8_has_fp16_weight": false,
     "llm_int8_skip_modules": null,
     "llm_int8_threshold": 6.0,
@@ -47,8 +48,9 @@
   },
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float16",
   "transformers_version": "4.43.2",
+  "unsloth_version": "2024.9",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -6,6 +6,8 @@
     128008,
     128009
   ],
+  "max_length": 131072,
+  "pad_token_id": 128004,
   "temperature": 0.6,
   "top_p": 0.9,
   "transformers_version": "4.43.2"

model-00001-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f04cbd8f2bc235453ea5457ccdda15d14d3d12a02de21b57111866b9a4d6f003
-size 4949082290
+oid sha256:06626cc36df91fa8f491492d49a8667f0fc6c5baf5039e47a6c112ed1050ad6e
+size 4949082282

model-00002-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd890071c67995f897924f539401984791acfbd5cb6c08f7ddd6394f43c2c7b8
-size 4977054940
+oid sha256:13d0ba8be2419a456d47a869130ee1408dae572d8493ad1957a987713f8f6dda
+size 4977054924

model-00003-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22b1f5d22b413e6043b431ccd4ff142b43b6788dbbcef009da272cf4826c0f37
-size 4977088094
+oid sha256:fdf855d777c1027687d58c3339d0d2471d07a4d716a70525b91afea9595c6ef1
+size 4977088070

model-00004-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab428b4f7c89d580c55e8283be380973f256d7ab92ae5ffb3280dcc8bcb48a9e
-size 4933786845
+oid sha256:277380f9abe8a90c3590fd893c2e449d3de520a7db45d78d8f129310679fb330
+size 4933786821

model-00005-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27bff8f0032f6b4ec5ca3e24d28cf30dd9f9deb86e3538a01f967218a7005bfd
-size 4977055132
+oid sha256:90dc73d070e86f0c3efd588459d9bc9760c522ff0811ac42e2d2106bf393414d
+size 4977055108

model-00006-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70e81ccd976d2e883ca2b79157b2223cc90d4ee38189f8194372bdedce0df244
-size 4977055097
+oid sha256:736ca29e715228a74a3259111a9429a439954a8d5ca66c01931b43d37aaa8efc
+size 4977055073

model-00007-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e78a6f4902f5dea55bfc57451a80b2790e0cc4c184f77c198395f8cc66bdca6
-size 4977088084
+oid sha256:dbc708907ac772ffdbfae645e7f9e10b3bca24b1521100e56e449bbf02840e2e
+size 4977088060

model-00008-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41ca67d01dffc9286724570664a9bd8e0a47eaa6f3459d85844aafb6a9e80dfb
-size 4750027590
+oid sha256:9ebdf1ac560da3a48c94f84e2b7702b031a55a690195807ad83eacaf9c22712d
+size 4750027574