Update config.json

config.json

@@ -9,24 +9,44 @@
     "AutoModel": "hf_utils.AutoModelForCausalLMWithRM"
   },
   "base_config": {
-    "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+    "_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
     "architectures": [
       "LlamaForCausalLM"
     ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
     "bos_token_id": 128000,
-    "eos_token_id": 128009,
+    "eos_token_id": [
+      128001,
+      128008,
+      128009
+    ],
+    "head_dim": 128,
+    "hidden_act": "silu",
     "hidden_size": 4096,
+    "initializer_range": 0.02,
     "intermediate_size": 14336,
-    "max_position_embeddings": 8192,
+    "max_position_embeddings": 131072,
+    "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": {
+      "factor": 8.0,
+      "high_freq_factor": 4.0,
+      "low_freq_factor": 1.0,
+      "original_max_position_embeddings": 8192,
+      "rope_type": "llama3"
+    },
     "rope_theta": 500000.0,
+    "tie_word_embeddings": false,
     "torch_dtype": "bfloat16",
-    "use_cache": false,
-    "vocab_size": 128257
+    "transformers_version": "4.46.0",
+    "use_cache": true,
+    "vocab_size": 128256
   },
   "base_model": "meta-llama/Meta-Llama-3-8B-Instruct",
   "bias": 0.0,