app.py

import gradio as gr
import spaces
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
from threading import Thread

MODEL_ID = "Qwen/Qwen2.5-1.5B-Instruct"

tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
model = AutoModelForCausalLM.from_pretrained(
    MODEL_ID,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

@spaces.GPU
def chat_function(message, history):
    messages = []
    for user_msg, assistant_msg in history:
        messages.append({"role": "user", "content": user_msg})
        messages.append({"role": "assistant", "content": assistant_msg})
    messages.append({"role": "user", "content": message})

    # 1. Render the chat template as a string
    prompt = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )

    # 2. Tokenize the string and move to the GPU
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

    streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
    
    # 3. Explicitly pass input_ids and attention_mask
    generation_kwargs = dict(
        input_ids=inputs["input_ids"],
        attention_mask=inputs["attention_mask"],
        streamer=streamer,
        max_new_tokens=512,
        do_sample=True,
        temperature=0.7,
        top_p=0.9
    )

    thread = Thread(target=model.generate, kwargs=generation_kwargs)
    thread.start()

    partial_text = ""
    for new_text in streamer:
        partial_text += new_text
        yield partial_text

demo = gr.ChatInterface(
    fn=chat_function,
    title="Qwen2.5-1.5B Chatbot",
    description="A lightweight LLM running on Hugging Face Spaces using ZeroGPU.",
)

if __name__ == "__main__":
    demo.launch()