Update app.py

app.py

@@ -18,7 +18,7 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 # ---------------------------------------------------------------------------
 # MODULE 4 — Generation Module (LLM setup)
 # ---------------------------------------------------------------------------
-MODEL_ID = "google/gemma-4-1b-it"   # swap for "google/gemma-4-9b-it" if VRAM allows
+MODEL_ID = "google/gemma-2b-it-tflite"   # swap for "google/gemma-4-9b-it" if VRAM allows
 
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 model = AutoModelForCausalLM.from_pretrained(