Create app.py

app.py

@@ -0,0 +1,21 @@
+from fastapi import FastAPI
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+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():
+    return {"message": "Welcome to QA GPT2 API 🚀"}
+
+@app.get("/ask")
+def ask(question: str, max_new_tokens: int = 50):
+    inputs = tokenizer(question, return_tensors="pt")
+    outputs = model.generate(**inputs, max_new_tokens=max_new_tokens)
+    answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return {"question": question, "answer": answer}