app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

# 載入模型和分詞器
model_name = "taide/Llama3-TAIDE-LX-8B-Chat-Alpha1"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

def chat_function(input_text):
    inputs = tokenizer(input_text, return_tensors="pt")
    output = model.generate(**inputs)
    response = tokenizer.decode(output[0], skip_special_tokens=True)
    return response

# 創建 Gradio 介面
iface = gr.Interface(fn=chat_function, inputs="text", outputs="text")
iface.launch()