update config

config.json

@@ -16,7 +16,16 @@
   "num_attention_heads": 40,
   "num_hidden_layers": 64,
   "num_key_value_heads": 8,
-  "quant_config": {
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064,
+  "quantization_config": {
     "model.layers.0.mlp.down_proj": {
       "bias": null,
       "enable_norm": true,
@@ -10768,15 +10777,7 @@
         -1,
         8
       ]
-    }
-  },
-  "rms_norm_eps": 1e-06,
-  "rope_theta": 1000000.0,
-  "sliding_window": null,
-  "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.37.2",
-  "use_cache": true,
-  "use_sliding_window": false,
-  "vocab_size": 152064
-}
+    },
+    "quant_method": "vptq"
+  }
+}