app.py

from fastapi import FastAPI
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

app = FastAPI()

# Define model-related constants
MODEL_NAME = "arnir0/Tiny-LLM"

# Global variables to store the tokenizer and model
tokenizer = None
model = None

@app.get("/")
def greet_json():
    global tokenizer, model

    # Load the model and tokenizer if not already loaded
    if model is None or tokenizer is None:
        tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
        model = AutoModelForCausalLM.from_pretrained(MODEL_NAME)
        model.eval()  # Set model to evaluation mode (optional for inference)

    return {"Hello": "World!", "model_status": "Loaded and hibernated!"}