app.py

import gradio as gr
from llama_cpp import Llama
import requests


llm = Llama.from_pretrained(
    repo_id="cognitivecomputations/dolphin-2.9.2-qwen2-7b-gguf",
    filename="*Q4_K_S.gguf",
    verbose=True,
    n_ctx=32768,
    n_threads=2,
    chat_format="chatml"
)

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 = ""
    response = llm.create_chat_completion(
            messages=messages,
            stream=True,
            max_tokens=max_tokens,
            temperature=temperature,
            top_p=top_p
        )
    message_repl = ""
    for chunk in response:
        if len(chunk['choices'][0]["delta"]) != 0 and "content" in chunk['choices'][0]["delta"]:
            message_repl = message_repl + \
                chunk['choices'][0]["delta"]["content"]
        yield message_repl
"""
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()