app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
from peft import PeftModel
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"

model_path = "Hack337/WavGPT-1.0" # Replace with the actual model path
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-1.5B-Instruct")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-1.5B-Instruct", 
                                             torch_dtype="auto", device_map="auto")

model = PeftModel.from_pretrained(model, model_path)


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})

    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(device)

    generated_ids = model.generate(
        model_inputs.input_ids,
        max_new_tokens=max_tokens,
        pad_token_id=tokenizer.eos_token_id,
        temperature=temperature,
        top_p=top_p
    )
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]
    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

    return response


demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="Вы очень полезный помощник.", 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()