app.py

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

model_name = "HuggingFaceTB/SmolLM3-3B"
TOKEN = os.getenv("HF_TOKEN")
device = "cuda" if torch.cuda.is_available() else "cpu"  # for GPU usage or "cpu" for CPU usage

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=TOKEN,
)
model = AutoModelForCausalLM.from_pretrained(
    model_name,use_auth_token=TOKEN,
).to(device)

def generate_text(prompt, max_length, temperature, top_p):
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(
        **inputs,
        max_new_tokens=max_length,
        temperature=0.6,
        top_p=0.95,
        pad_token_id=tokenizer.eos_token_id
    )
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# prepare the model input
prompt = "Give me a brief explanation of gravity in simple terms."
messages_think = [
    {"role": "user", "content": prompt}
]

text = tokenizer.apply_chat_template(
    messages_think,
    tokenize=False,
    add_generation_prompt=True,
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate the output
generated_ids = model.generate(**model_inputs, max_new_tokens=32768)

# Get and decode the output
output_ids = generated_ids[0][len(model_inputs.input_ids[0]) :]
print(tokenizer.decode(output_ids, skip_special_tokens=True))

# Build Gradio interface
interface = gr.Interface(
    fn=generate_text,
    inputs="text",        # single text‐in box
    outputs="text",       # single text‐out box
    title="SmolLM3-3B Demo",
    description="Type your prompt and hit Submit"
)

if __name__ == "__main__":
    interface.launch()   # on Spaces this will auto-bind correctly