app.py

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

model_id = "Nihal2000/gemma3-merged"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

gen = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    device=0 if "CUDA_VISIBLE_DEVICES" in os.environ else -1
)

def respond(message, history, system_message, max_tokens, temperature, top_p):
    prompt = system_message + "\n" + "\n".join(
        [f"User: {u}\nAssistant: {a}" for u, a in history]
    ) + f"\nUser: {message}\nAssistant:"
    out = gen(
        prompt,
        max_new_tokens=max_tokens,
        temperature=temperature,
        top_p=top_p,
        do_sample=False,
    )
    # Return current assistant final response
    response = out[0]["generated_text"][len(prompt):]
    return response

chatbot = gr.ChatInterface(
    respond,
    type="messages",
    additional_inputs=[
        gr.Textbox(value="You are an automotive assistant.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=2.0, 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"),
    ]
)

with gr.Blocks() as demo:
    chatbot.render()

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