app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM
from huggingface_hub import login
import os

# Retrieve the Hugging Face token from the Space secrets
token = os.getenv("HF_TOKEN")

# Log in using the token
login(token=token)


# Load model and tokenizer
model_name = "meta-llama/Llama-3.2-1B"  # Replace with the correct model name if necessary
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Define inference function
def generate_text(input_text):
    inputs = tokenizer(input_text, return_tensors="pt")
    outputs = model.generate(inputs["input_ids"], max_length=50, num_return_sequences=1)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response

# Create Gradio interface
iface = gr.Interface(fn=generate_text, inputs="text", outputs="text")

# Launch the interface
iface.launch()