Update app.py

app.py

@@ -18,9 +18,8 @@ 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-3-1b-it"   # swap for "google/gemma-4-9b-it" if VRAM allows
 
-print(f"[Generation] Loading model: {MODEL_ID}")
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_ID,
@@ -34,7 +33,7 @@ pipe = pipeline(
     max_new_tokens=512,
     do_sample=False,                      # deterministic output
 )
-print("[Generation] Model ready.")
+
 
 
 # ---------------------------------------------------------------------------