Update README.md

README.md

@@ -252,7 +252,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, TorchAoConfig
 
 # use "microsoft/Phi-4-mini-instruct" or "pytorch/Phi-4-mini-instruct-INT4"
 model_id = "pytorch/Phi-4-mini-instruct-INT4"
-quantized_model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype=torch.bfloat16)
+quantized_model = AutoModelForCausalLM.from_pretrained(model_id, device_map="cuda:0", torch_dtype=torch.bfloat16)
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 
 torch.cuda.reset_peak_memory_stats()