Update README.md

README.md

@@ -40,14 +40,14 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, TorchAoConfig
 model_id = "microsoft/Phi-4-mini-instruct"
 
 from torchao.quantization import Int4WeightOnlyConfig
-quant_config = Int4WeightOnlyConfig(group_size=128)
+quant_config = Int4WeightOnlyConfig(group_size=128, use_hqq=True)
 quantization_config = TorchAoConfig(quant_type=quant_config)
 quantized_model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype=torch.bfloat16, quantization_config=quantization_config)
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 
 # Push to hub
 USER_ID = "YOUR_USER_ID"
-save_to = f"{USER_ID}/{model_id}-int4wo"
+save_to = f"{USER_ID}/{model_id}-int4wo-hqq"
 quantized_model.push_to_hub(save_to, safe_serialization=False)
 tokenizer.push_to_hub(save_to)