app.py

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

# Load model and tokenizer from HuggingFace
model_name = "HuggingFaceTB/SmolLM2-135M"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

def generate(prompt, max_length=50, temperature=0.7):
    """Generate text from prompt"""
    inputs = tokenizer(prompt, return_tensors="pt")
    
    # Generate text
    outputs = model.generate(
        **inputs,
        max_new_tokens=max_length,
        temperature=temperature,
        do_sample=True,
        top_p=0.9,
        repetition_penalty=1.1
    )
    
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Create Gradio interface
demo = gr.Interface(
    fn=generate,
    inputs=[
        gr.Textbox(label="Enter your prompt", value="Once upon a time"),
        gr.Slider(minimum=10, maximum=200, value=50, label="Maximum length"),
        gr.Slider(minimum=0.1, maximum=1.0, value=0.7, label="Temperature")
    ],
    outputs=gr.Textbox(label="Generated Text"),
    title="SmolLM2 Text Generation",
    description="A small language model based on SmolLM2-135M architecture."
)

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