Update app.py

app.py

@@ -5,8 +5,8 @@ import torch
 zephyr_tokenizer = AutoTokenizer.from_pretrained("HuggingFaceH4/zephyr-7b-alpha")
 zephyr_model = AutoModelForCausalLM.from_pretrained(
     "HuggingFaceH4/zephyr-7b-alpha",
-    #torch_dtype=torch.float16,  # Use half-precision for faster inference
-    #device_map="auto"  # Automatically loads the model on GPU if available
+    torch_dtype=torch.float16,  # Use half-precision for faster inference
+    device_map="auto"  # Automatically loads the model on GPU if available
 )
 
 def generate_response(prompt):