app.py

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

import os


# Set cache directory for Hugging Face Transformers
os.environ["TRANSFORMERS_CACHE"] = "/home/user/.cache"

# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("matsant01/STEMerald-2b")
model = AutoModelForCausalLM.from_pretrained("matsant01/STEMerald-2b")

# Initialize FastAPI app
app = FastAPI()



@app.get("/")
def read_root():
    return {"message": "Welcome to the STEMerald-2b API"}

#@app.post("/generate/")
#def generate_text(prompt: str):
#    inputs = tokenizer(prompt, return_tensors="pt")
#    outputs = model.generate(inputs["input_ids"], max_length=50)
#    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
#    return {"generated_text": generated_text}