fix: Replace incorrect 1.2B config with correct 3B ORPO config (hidden_size=3072, 28 layers, vocab=64256)

config.json

@@ -2,21 +2,31 @@
   "architectures": [
     "LlamaForCausalLM"
   ],
-  "model_type": "llama",
-  "hidden_size": 2048,
-  "intermediate_size": 5472,
-  "num_hidden_layers": 24,
-  "num_attention_heads": 16,
-  "num_key_value_heads": 4,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 128,
   "hidden_act": "silu",
-  "max_position_embeddings": 4096,
+  "hidden_size": 3072,
   "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
-  "vocab_size": 64256,
-  "rope_theta": 500000.0,
-  "rope_scaling": null,
-  "attention_bias": false,
+  "rope_parameters": {
+    "rope_theta": 500000.0,
+    "rope_type": "default"
+  },
   "tie_word_embeddings": true,
-  "torch_dtype": "float16",
-  "transformers_version": "4.40.0"
+  "transformers_version": "5.2.0",
+  "use_cache": false,
+  "vocab_size": 64256
 }