app.py

import gradio as gr
from huggingface_hub import InferenceClient
import spaces
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
from transformers import pipeline

pipe = pipeline("text-generation", model="BioMistral/BioMistral-7B", torch_dtype=torch.bfloat16, device_map="auto")


@spaces.GPU
def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
    hf_token,
):

    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 = ""
    
    prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    outputs = pipe(prompt, max_new_tokens=max_tokens, do_sample=True, temperature=temperature, top_k=50, top_p=top_p)
    last_space_index = outputs[0]["generated_text"].rfind('[/INST]')
# Extract the substring after the last space character
    substring_after_last_space = outputs[0]["generated_text"][last_space_index + 7:]
    yield substring_after_last_space


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)",
    
        ),
        gr.Textbox(label="Hugging Face Token", placeholder="Enter your Hugging Face token here"),
    ],
    css="footer{display:none !important}",
)


if __name__ == "__main__":
    demo.launch()