app.py

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

# Load the model locally
model_name = "bigchestnut/mob213"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype=torch.float16)

def respond(message, history, system_message, max_tokens, temperature, top_p):
    # Prepare input prompt
    prompt = system_message + "\n" + "\n".join(
        [f"User: {h[0]}\nAssistant: {h[1]}" for h in history if h[0] and h[1]]
    ) + f"\nUser: {message}\nAssistant:"

    inputs = tokenizer(prompt, return_tensors="pt")
    with torch.no_grad():
        outputs = model.generate(**inputs, max_new_tokens=max_tokens, temperature=temperature, top_p=top_p)

    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response

demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a helpful assistant.", 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)