| from transformers import AutoTokenizer, AutoModel | |
| model_path = "THUDM/chatglm2-6b" | |
| tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True) | |
| model = AutoModel.from_pretrained(model_path,trust_remote_code=True).half().quantize(4) | |
| model = model.eval() | |
| resp, history = model.chat(tokenizer, "美国的首都是哪里", history=[]) | |
| print(resp) |