Ian-14/model_test

How to use

from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b-int4", trust_remote_code=True)
model = AutoModel.from_pretrained("THUDM/chatglm2-6b-int4", trust_remote_code=True).half().cuda()
model = model.eval()
text = "你好"
response, history = model.chat(tokenizer, text, history=[])
response