app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM

MODEL_ID = "Xen0pp/SmolLM-ML-Planner-500-V3"

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

def generate_text(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=150)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

iface = gr.Interface(
    fn=generate_text,
    inputs=gr.Textbox(label="Enter Prompt"),
    outputs=gr.Textbox(label="Response"),
    title="ML Planner API"
)

iface.launch()