llama3 0630

models/dummy_model.py

@@ -41,7 +41,7 @@ class llama3_8b_FewShot_vllm(ShopBenchBaseModel):
 
     def initialize_models(self):
         # Initialize Meta Llama 3 - 8B Instruct Model
-        self.model_name = "./models/qwen2-0630"
+        self.model_name = "./models/llama3-0630"
 
         if not os.path.exists(self.model_name):
             raise Exception(

models/llama3-0630/config.json

+{
+  "_name_or_path": "/root/models/llama3",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "vocab_size": 128256
+}

models/llama3-0630/generation_config.json

+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.42.3"
+}

models/llama3-0630/special_tokens_map.json

+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/lora_module_merge.sh

 python lora_module_merge.py  \
     --base_model_name_or_path /root/models/llama3 \
-    --lora_path ./adapter \
+    --lora_path /root/adapter \
     --merged_model_save_path /root/autodl-tmp/models/llama3-0630
\ No newline at end of file