app.py

from __future__ import annotations
import os
os.environ["GRADIO_ANALYTICS_ENABLED"] = "False"
import gradio as gr
from llama_cpp import Llama

llm = Llama.from_pretrained(
    repo_id="matteogeniaccio/phi-4",
    filename="phi-4-Q4_K_M.gguf",
    verbose=True
)

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    # 构造消息内容
    messages = [{"role": "system", "content": system_message}]
    for user_msg, assistant_msg in history:
        if user_msg:
            messages.append({"role": "user", "content": user_msg})
        if assistant_msg:
            messages.append({"role": "assistant", "content": assistant_msg})
    messages.append({"role": "user", "content": message})

    # 使用llama-cpp-python的方式生成响应
    response = llm.create_chat_completion(
        messages=messages,
        max_tokens=max_tokens,
        temperature=temperature,
        top_p=top_p,
        stream=True
    )

    # 流式响应处理
    partial_message = ""
    for chunk in response:
        if chunk and chunk.get("choices") and chunk["choices"][0].get("delta", {}).get("content"):
            content = chunk["choices"][0]["delta"]["content"]
            partial_message += content
            yield partial_message

# Gradio 界面
with gr.Blocks() as demo:
    gr.Markdown("You must be logged in to use GGUF-my-lora.")
    gr.LoginButton(min_width=250)
    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()