app.py

import gradio as gr
import accelerate 
import bitsandbytes
"""
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
"""
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "MaziyarPanahi/Mistral-7B-Instruct-Aya-101-GGUF"
filename = "Mistral-7B-Instruct-Aya-101.Q8_0.gguf"

tokenizer = AutoTokenizer.from_pretrained(model_id, gguf_file=filename)
model = AutoModelForCausalLM.from_pretrained(model_id, gguf_file=filename)
def respond(
    message,
    max_new_tokens=4000,
    temperature=0.3,
    top_p = 0.7,
):


    messages = [{"role": "user", "content": f"{message}"}]
    input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")

    gen_tokens = model.generate(
        input_ids,
        max_new_tokens=max_new_tokens,
        do_sample=True,
        temperature=temperature,
        top_p=top_p
        )

    gen_text = tokenizer.decode(gen_tokens[0])
    yield gen_text

"""
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()