Update app.py

app.py

@@ -1,13 +1,18 @@
 from fastapi import FastAPI
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
+import os
+
+
+os.environ["TRANSFORMERS_CACHE"] = "/app/cache"
+
+model_id = "rabiyulfahim/qa_python_gpt2"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id, cache_dir="/app/cache")
+model = AutoModelForCausalLM.from_pretrained(model_id, cache_dir="/app/cache")
 
 app = FastAPI(title="QA GPT2 API", description="Serving HuggingFace model with FastAPI")
 
-# Load model once on startup
-model_id = "rabiyulfahim/qa_python_gpt2"   # 👈 replace with your HF repo
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id)
 
 @app.get("/")
 def home():