Update app/app.py

app/app.py

@@ -16,6 +16,8 @@ print("Vector Database loaded successfully!")
 model_id = "Kalpokoch/QuantizedTinyLama"  # Correct spelling assumed
 print(f"Loading model: {model_id}...")
 tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+print("Model and tokenizer loaded successfully!")
 
 # Choose dtype depending on device support
 dtype = torch.bfloat16 if torch.cuda.is_available() and torch.cuda.is_bf16_supported() else torch.float16