Update README.md

README.md

@@ -37,7 +37,7 @@ datasets:
 >>> from transformers import AutoTokenizer, TextStreamer
 >>> from auto_gptq import AutoGPTQForCausalLM
 >>> tokenizer = AutoTokenizer.from_pretrained("fireballoon/baichuan-vicuna-chinese-7b-gptq", use_fast=False)
->>> model = AutoGPTQForCausalLM.from_pretrained("fireballoon/baichuan-vicuna-chinese-7b-gptq").cuda()
+>>> model = AutoGPTQForCausalLM.from_quantized("fireballoon/baichuan-vicuna-chinese-7b-gptq", device="cuda:0")
 >>> streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
 >>> instruction = "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {} ASSISTANT:"
 >>> prompt = instruction.format("How can I improve my time management skills?")  # user message