app.py

import gradio as gr
from huggingface_hub import InferenceClient

# Replace with your model ID
client = InferenceClient("Saibalaji25/autotrain-0u37b-accmn")

def respond(message, history, system_message, max_tokens, temperature, top_p):
    # Format the prompt (you can add system_message before if needed)
    prompt = message

    # Get the output from the model
    output = client.text_generation(
        prompt=prompt,
        max_new_tokens=max_tokens,
        temperature=temperature,
        top_p=top_p,
        stream=False,  # True is only useful if you handle streamed responses
    )

    return output

demo = gr.ChatInterface(
    fn=respond,
    additional_inputs=[
        gr.Textbox(value="You are a helpful code assistant. Complete the following code.", label="System message"),
        gr.Slider(minimum=1, maximum=1024, value=256, 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=0.9, step=0.05, label="Top-p"),
    ],
)

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