Update config.json

config.json

@@ -1,16 +1,40 @@
 {
-  "architectures": ["LlamaForCausalLM"],
-  "model_type": "llama",
-  "hidden_size": 3200,
-  "intermediate_size": 12800,
-  "num_attention_heads": 32,
-  "num_hidden_layers": 30,
-  "max_position_embeddings": 2048,
-  "vocab_size": 32000,
+  "_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
   "initializer_range": 0.02,
-  "layer_norm_eps": 1e-6,
-  "pad_token_id": 0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "use_cache": true
-}
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "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": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0",
+  "use_cache": true,
+  "vocab_size": 128256
+}