update config

config.json

@@ -22,7 +22,21 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
-  "quant_config": {
+  "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",
+  "transformers_version": "4.45.1",
+  "use_cache": true,
+  "vocab_size": 128256,
+  "quantization_config": {
     "model.layers.0.mlp.down_proj": {
       "bias": false,
       "enable_norm": true,
@@ -5398,20 +5412,7 @@
         -1,
         8
       ]
-    }
-  },
-  "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",
-  "transformers_version": "4.45.1",
-  "use_cache": true,
-  "vocab_size": 128256
-}
+    },
+    "quant_method": "vptq"
+  }
+}