pip install bitsandbytes
from modelscope import AutoTokenizer, AutoModel, snapshot_download model_dir = "E:\project\pythonProject1f\ZhipuAI" tokenizer = AutoTokenizer.from_pretrained(model_dir, trust_remote_code=True) #model = AutoModel.from_pretrained(model_dir, trust_remote_code=True).half().cuda() model = AutoModel.from_pretrained(model_dir, load_in_4bit=True, trust_remote_code=True) model = model.eval() response, history = model.chat(tokenizer, "你好", history=[]) print(response) response, history = model.chat(tokenizer, "晚上睡不着应该怎么办", history=history) print(response)