app.py

from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer, TextIteratorStreamer
from threading import Thread
import gradio as gr

model = AutoPeftModelForCausalLM.from_pretrained("adlsdztony/Rui-0.5B")
tokenizer = AutoTokenizer.from_pretrained("adlsdztony/Rui-3B")


# from huggingface_hub import InferenceClient

# """
# For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
# """
# client = InferenceClient("adlsdztony/Rui-3B")


def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    messages.append({"role": "user", "content": message})


    prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    
    inputs = tokenizer([prompt], return_tensors='pt', padding=True, truncation=True)

    streamer = TextIteratorStreamer(tokenizer)
    generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=max_tokens, do_sample=True, temperature=temperature, top_p=top_p)

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

    generate_text = ''
    for new_text in streamer:
        output = new_text.replace(prompt, '')
        if output:
            generate_text += output
            yield generate_text

    # response = ""

    # for message in client.chat_completion(
    #     messages,
    #     max_tokens=max_tokens,
    #     stream=True,
    #     temperature=temperature,
    #     top_p=top_p,
    # ):
    #     token = message.choices[0].delta.content

    #     response += token
    #     yield response


"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="你是小锐，你只会说中文，你会自称为‘锐’，你的工作是每天告诉同学明天的天气和一些最近发生的事情，最后你会跟同学说晚安", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
)


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