app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
# Load model
model_name = "HOANGHUAN/dulich"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.float16,
    device_map="auto"
)
def chat(message, history):
    messages = [
        {"role": "system", "content": "Bạn là Vistours Assistant."},
        {"role": "user", "content": message}
    ]
    
    prompt = tokenizer.apply_chat_template(messages, tokenize=False)
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    
    outputs = model.generate(
        **inputs,
        max_new_tokens=256,
        temperature=0.7,
        top_p=0.9,
        do_sample=True
    )
    
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    # Extract assistant response
    if "assistant" in response:
        response = response.split("assistant")[-1].strip()
    return response
gr.ChatInterface(
    fn=chat,
    title="Vistours Chatbot",
    description="AI Assistant cho công ty du lịch Vistours"
).launch()