app.py

import json
import spaces
import subprocess
import gradio as gr
from llama_cpp import Llama
from llama_cpp_agent.chat_history.messages import Roles
from llama_cpp_agent.chat_history import BasicChatHistory
from llama_cpp_agent.providers import LlamaCppPythonProvider
from llama_cpp_agent import LlamaCppAgent, MessagesFormatterType
from huggingface_hub import InferenceClient
from huggingface_hub import hf_hub_download

"""
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
"""
SYSTEM = "You are a helpful math assistant. You should always provide your answer in Chinese."

client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
hf_hub_download(
    repo_id="bartowski/Qwen2.5-Math-7B-Instruct-GGUF",
    filename="Qwen2.5-Math-7B-Instruct-Q8_0.gguf",
    local_dir="./models"
)

llm = Llama(
    model_path="models/Qwen2.5-Math-7B-Instruct-Q8_0.gguf",
    flash_attn=True,
    n_ctx=8192,
    n_batch=1024
)

provider = LlamaCppPythonProvider(llm)

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()