app.py

import gradio as gr
from huggingface_hub import InferenceClient
from llama_cpp import Llama
from llama_cpp.llama_chat_format import MoondreamChatHandler

chat_handler = MoondreamChatHandler.from_pretrained(
  repo_id="vikhyatk/moondream2",
  filename="*mmproj*",
)


llm = Llama.from_pretrained(
	repo_id="eybro/model2",
	filename="unsloth.Q4_K_M.gguf",
    chat_handler=chat_handler,
    n_ctx=2048,
)



"""
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")

client = InferenceClient("eybro/model")

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    # Simplified to handle only text input (no image input)
    messages = [{"role": "user", "content": message}]

    # Use llm to generate the response
    response = ""
    try:
        completion = llm.create_chat_completion(
            messages=messages,
        )
        response = completion['choices'][0]['message']['content']
    except Exception as e:
        response = f"Error: {e}"

    return 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()