Update app.py

app.py

@@ -35,7 +35,7 @@ def load_quantized_model(model_id, model_basename):
 
 
 # Making the code device-agnostic
-model, tokenizer = load_quantized_model(model_name_or_path, "model.safetensors")
+#model, tokenizer = load_quantized_model(model_name_or_path, "model.safetensors")
 
 def load_model_norm():
     if torch.cuda.is_available():
@@ -53,7 +53,7 @@ def load_model_norm():
     return model, tokenizer 
 
 
-#model, tokenizer = load_model_norm()
+model, tokenizer = load_model_norm()
 
     
 # Function to generate a response using the model