Update app.py

app.py

@@ -4,7 +4,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 import os
 
 # Model configuration
-MODEL_NAME = "your-username/your-model-name"  # Replace with your actual HF model repo
+MODEL_NAME = "model.safetensors"  # Replace with your actual HF model repo
 DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
 
 # Load model and tokenizer