app.py

import os
import subprocess
import torch
import gradio as gr
from huggingface_hub import InferenceClient
from vllm.config import DeviceConfig
from vllm import LLM
from sal.models.reward_models import RLHFFlow

if not os.path.exists("search-and-learn"):
    subprocess.run(["git", "clone", "https://github.com/huggingface/search-and-learn"])
    subprocess.run(["pip", "install", "-e", "./search-and-learn[dev]"])


device_config = DeviceConfig(device=torch.device('cuda' if torch.cuda.is_available() else 'cpu'))
print('device_config', device_config)
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print('device', device)


model_path = "meta-llama/Llama-3.2-1B-Instruct"
prm_path = "RLHFlow/Llama3.1-8B-PRM-Deepseek-Data"

llm = LLM(
    model=model_path,
    gpu_memory_utilization=0.5,  # Utilize 50% of GPU memory
    enable_prefix_caching=True,  # Optimize repeated prefix computations
    seed=42,  # Set seed for reproducibility
)


"""
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("HuggingFaceH4/zephyr-7b-beta")



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})

    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="You are a friendly Chatbot.", 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()