Updated compression_config to quantization_config

config.json

@@ -5,7 +5,26 @@
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "compression_config": {
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 12288,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 96,
+  "num_hidden_layers": 88,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32768,
+  "quantization_config": {
     "config_groups": {
       "group_0": {
         "input_activations": {
@@ -44,24 +63,5 @@
     "kv_cache_scheme": null,
     "quant_method": "compressed-tensors",
     "quantization_status": "frozen"
-  },
-  "eos_token_id": 2,
-  "head_dim": 128,
-  "hidden_act": "silu",
-  "hidden_size": 12288,
-  "initializer_range": 0.02,
-  "intermediate_size": 28672,
-  "max_position_embeddings": 131072,
-  "model_type": "mistral",
-  "num_attention_heads": 96,
-  "num_hidden_layers": 88,
-  "num_key_value_heads": 8,
-  "rms_norm_eps": 1e-05,
-  "rope_theta": 1000000.0,
-  "sliding_window": null,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.44.0.dev0",
-  "use_cache": true,
-  "vocab_size": 32768
+  }
 }