app.py

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

# Load your model and tokenizer locally
model_name = "william590y/AshishGPT"  # Replace with your Hugging Face model name
print("Loading model and tokenizer...")
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
print("Model loaded successfully!")

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    # Prepare the input context from history
    input_text = system_message + "\n"
    for user_input, bot_response in history:
        input_text += f"User: {user_input}\nAssistant: {bot_response}\n"
    input_text += f"User: {message}\nAssistant:"

    # Tokenize input and generate response
    inputs = tokenizer(input_text, return_tensors="pt", truncation=True).to("cuda")
    outputs = model.generate(
        **inputs,
        max_new_tokens=max_tokens,
        temperature=temperature,
        top_p=top_p,
        pad_token_id=tokenizer.eos_token_id,
    )
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)

    # Extract the assistant's response
    response = response[len(input_text):].strip()
    return response


# Set up the Gradio interface
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()