app.py

import gradio as gr
from huggingface_hub import InferenceClient

client = InferenceClient("bigscience/bloom")

def generate_text(prompt, max_tokens, temperature, top_p):
    try:
        response = client.chat_completion(
            [{"role": "user", "content": prompt}],
            max_tokens=max_tokens,
            stream=True,
            temperature=temperature,
            top_p=top_p,
        )
        return response
    except Exception as e:
        return str(e)

demo = gr.Interface(
    fn=generate_text,
    inputs=[
        gr.Textbox(label="Prompt"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max 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)"),
    ],
    outputs="text",
    title="Text Generation",
    description="Generate text based on input prompt and parameters."
)

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