app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("THUDM/codegeex2-6b", trust_remote_code=True)
model = AutoModel.from_pretrained("THUDM/codegeex2-6b", trust_remote_code=True)
model = model.eval()

def greet(prompt):
    inputs = tokenizer.encode(prompt, return_tensors="pt").to(model.device)
    outputs = model.generate(inputs, max_length=256, top_k=1)
    response = tokenizer.decode(outputs[0])
    return response

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