import gradio as gr from transformers import AutoTokenizer, AutoModelForCausalLM model_name = "Qwen/Qwen2.5-Coder-7B-Instruct" tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained( model_name, device_map="auto", torch_dtype="auto", trust_remote_code=True ) def chat(message, history): inputs = tokenizer(message, return_tensors="pt") output = model.generate(**inputs, max_new_tokens=300) reply = tokenizer.decode(output[0], skip_special_tokens=True) return reply gr.ChatInterface(fn=chat).launch()