Update app.py

app.py

@@ -9,6 +9,7 @@ HF_TOKEN = os.getenv("HF_TOKEN")  # đọc token từ Secrets
 
 client = InferenceClient(token=HF_TOKEN, model=MODEL_ID)
 
+
 @app.get("/")
 def root():
     return {"message": "Gemma 3 API on CPU"}
@@ -17,10 +18,13 @@ def root():
 @app.post("/generate")
 async def generate(request: Request):
     body = await request.json()
+    
     prompt = body.get("prompt", "")
     max_new_tokens = body.get("max_new_tokens", 128)
     temperature = body.get("temperature", 0.7)
 
+    print(HF_TOKEN)
+    
     out = client.text_generation(prompt, max_new_tokens=200)
 
     return {"text": out}