Updated compression_config to quantization_config

config.json

@@ -7,7 +7,32 @@
   "attention_dropout": 0.1,
   "attention_softmax_in_fp32": true,
   "bos_token_id": 0,
-  "compression_config": {
+  "embedding_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_size": 4608,
+  "initializer_range": 0.018042,
+  "intermediate_size": 18432,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 16384,
+  "mlp_type": "default",
+  "model_type": "starcoder2",
+  "norm_epsilon": 1e-05,
+  "norm_type": "layer_norm",
+  "num_attention_heads": 36,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 4,
+  "residual_dropout": 0.1,
+  "rope_theta": 1000000,
+  "scale_attention_softmax_in_fp32": true,
+  "scale_attn_weights": true,
+  "sliding_window": 4096,
+  "torch_dtype": "float16",
+  "transformers_version": "4.44.0.dev0",
+  "use_bias": true,
+  "use_cache": true,
+  "vocab_size": 49152,
+  "quantization_config": {
     "config_groups": {
       "group_0": {
         "input_activations": {
@@ -46,30 +71,5 @@
     "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": 4608,
-  "initializer_range": 0.018042,
-  "intermediate_size": 18432,
-  "layer_norm_epsilon": 1e-05,
-  "max_position_embeddings": 16384,
-  "mlp_type": "default",
-  "model_type": "starcoder2",
-  "norm_epsilon": 1e-05,
-  "norm_type": "layer_norm",
-  "num_attention_heads": 36,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 4,
-  "residual_dropout": 0.1,
-  "rope_theta": 1000000,
-  "scale_attention_softmax_in_fp32": true,
-  "scale_attn_weights": true,
-  "sliding_window": 4096,
-  "torch_dtype": "float16",
-  "transformers_version": "4.44.0.dev0",
-  "use_bias": true,
-  "use_cache": true,
-  "vocab_size": 49152
+  }
 }