Updated compression_config to quantization_config

config.json

@@ -5,7 +5,27 @@
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
-  "compression_config": {
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936,
+  "quantization_config": {
     "config_groups": {
       "group_0": {
         "input_activations": null,
@@ -34,25 +54,5 @@
     "kv_cache_scheme": null,
     "quant_method": "compressed-tensors",
     "quantization_status": "frozen"
-  },
-  "eos_token_id": 151645,
-  "hidden_act": "silu",
-  "hidden_size": 1536,
-  "initializer_range": 0.02,
-  "intermediate_size": 8960,
-  "max_position_embeddings": 32768,
-  "max_window_layers": 28,
-  "model_type": "qwen2",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 2,
-  "rms_norm_eps": 1e-06,
-  "rope_theta": 1000000.0,
-  "sliding_window": 32768,
-  "tie_word_embeddings": true,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.42.4",
-  "use_cache": true,
-  "use_sliding_window": false,
-  "vocab_size": 151936
+  }
 }