app.py

import os
import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM

access_token = os.getenv('HF_TOKEN')

# Define the repository ID and access token
repo_id = "Mikhil-jivus/Llama-32-3B-FineTuned"
access_token = "your_access_token_here"

# Load the tokenizer and model from the Hugging Face repository
tokenizer = AutoTokenizer.from_pretrained(repo_id, use_auth_token=access_token)
model = AutoModelForCausalLM.from_pretrained(repo_id, use_auth_token=access_token)

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})

    # Tokenize the input messages
    input_text = system_message + " ".join([f"{msg['role']}: {msg['content']}" for msg in messages])
    input_ids = tokenizer.encode(input_text, return_tensors="pt")

    # Create attention mask
    attention_mask = input_ids.ne(tokenizer.pad_token_id).long()

    # Generate a response
    chat_history_ids = model.generate(
        input_ids,
        max_length=max_tokens,
        temperature=temperature,
        top_p=top_p,
        pad_token_id=tokenizer.eos_token_id,
        do_sample=True,
        attention_mask=attention_mask,
    )

    # Decode the response
    response = tokenizer.decode(chat_history_ids[:, input_ids.shape[-1]:][0], skip_special_tokens=True)

    yield 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(share=True)