Updated compression_config to quantization_config

config.json

@@ -5,7 +5,30 @@
   ],
   "attention_dropout": 0.1,
   "bos_token_id": 0,
-  "compression_config": {
+  "embedding_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_size": 6144,
+  "initializer_range": 0.01275,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 16384,
+  "mlp_type": "default",
+  "model_type": "starcoder2",
+  "norm_epsilon": 1e-05,
+  "norm_type": "layer_norm",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 4,
+  "residual_dropout": 0.1,
+  "rope_theta": 100000,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.3",
+  "use_bias": true,
+  "use_cache": true,
+  "vocab_size": 49152,
+  "quantization_config": {
     "config_groups": {
       "group_0": {
         "input_activations": null,
@@ -34,28 +57,5 @@
     "kv_cache_scheme": null,
     "quant_method": "compressed-tensors",
     "quantization_status": "frozen"
-  },
-  "embedding_dropout": 0.1,
-  "eos_token_id": 0,
-  "hidden_act": "gelu_pytorch_tanh",
-  "hidden_size": 6144,
-  "initializer_range": 0.01275,
-  "intermediate_size": 24576,
-  "max_position_embeddings": 16384,
-  "mlp_type": "default",
-  "model_type": "starcoder2",
-  "norm_epsilon": 1e-05,
-  "norm_type": "layer_norm",
-  "num_attention_heads": 48,
-  "num_hidden_layers": 40,
-  "num_key_value_heads": 4,
-  "residual_dropout": 0.1,
-  "rope_theta": 100000,
-  "sliding_window": 4096,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.43.3",
-  "use_bias": true,
-  "use_cache": true,
-  "vocab_size": 49152
+  }
 }