app.py

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

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

# Get Hugging Face API token
HF_API_TOKEN = os.getenv("HF_API_TOKEN")
if not HF_API_TOKEN:
    raise ValueError("HF_API_TOKEN environment variable is not set!")

app = FastAPI()

# Load Falcon 7B model
MODEL_NAME = "SpiceyToad/demo-falc"
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, token=HF_API_TOKEN)
model = AutoModelForCausalLM.from_pretrained(
    MODEL_NAME,
    device_map="auto",
    torch_dtype=torch.bfloat16,
    token=HF_API_TOKEN
)

@app.post("/generate")
async def generate_text(request: Request):
    data = await request.json()
    prompt = data.get("prompt", "")
    max_length = data.get("max_length", 50)

    # Tokenize and generate
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    outputs = model.generate(inputs["input_ids"], max_length=max_length)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return {"generated_text": response}