示例代码里还是THUDM/chatglm2-6b,没有改成chatglm2-6b-int4tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True)model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).half().cuda()
· Sign up or log in to comment