app.py

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

# Load model and tokenizer
model_name = "Magpie-Align/MagpieLM-8B-Chat-v0.1"

device = "cuda" # the device to load the model onto
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
)
model.to(device)

MAX_INPUT_TOKEN_LENGTH = 4096  # You may need to adjust this value

@spaces.GPU
def respond(
    message: str,
    chat_history: list[tuple[str, str]],
    system_prompt: str,
    max_new_tokens: int = 1024,
    temperature: float = 0.6,
    top_p: float = 0.9,
    top_k: int = 50,
    repetition_penalty: float = 1.2,
) -> Iterator[str]:
    conversation = []
    if system_prompt:
        conversation.append({"role": "system", "content": system_prompt})
    for user, assistant in chat_history:
        conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
    conversation.append({"role": "user", "content": message})

    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
    if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
        input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
        gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
    input_ids = input_ids.to(model.device)

    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
    generate_kwargs = dict(
        input_ids=input_ids,
        streamer=streamer,
        max_new_tokens=max_new_tokens,
        do_sample=True,
        top_p=top_p,
        top_k=top_k,
        temperature=temperature,
        num_beams=1,
        repetition_penalty=repetition_penalty,
    )
    t = Thread(target=model.generate, kwargs=generate_kwargs)
    t.start()

    outputs = []
    for text in streamer:
        outputs.append(text)
        yield "".join(outputs)

demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are Magpie, a helpful AI assistant.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=1024, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.6, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.9,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
        gr.Slider(minimum=0.5, maximum=1.5, value=1.0, step=0.1, label="Repetation Penalty"),
    ],
)


if __name__ == "__main__":
    demo.queue()
    demo.launch(share=True)