demo_app.py

from transformers import AutoTokenizer, AutoModel
import gradio as gr

tokenizer = AutoTokenizer.from_pretrained(".\\models\\chatglm-6b-int4", trust_remote_code=True, revision="")
model = AutoModel.from_pretrained(".\\models\\chatglm-6b-int4", trust_remote_code=True, revision="").half().cuda()
model = model.eval()



def chat(msg):
    history = []
    response, history = model.chat(tokenizer, msg, history=history)
    print("response:", response)
    return response


iface = gr.Interface(fn=chat, inputs="text", outputs="text")
iface.launch()