Upload LlamaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "unsloth/llama-3-8b",
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -17,13 +17,27 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.1",
-  "unsloth_version": "2024.4",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -1,9 +1,9 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 128000,
-  "eos_token_id": [
-    128001,
-    128009
-  ],
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
   "transformers_version": "4.40.1"
 }

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fc207a5587abffede1b50ce275dd6967ecb4a373c82abf53b9e1d466404a139
+size 4652073157

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b09b2f5119431f75c6dbcce7a5048894e87c519bdd3f4f162def6b1de2dc0f6
+size 1050673280