Update app.py

app.py

@@ -3,7 +3,6 @@ import gradio as gr
 from transformers import LlamaTokenizer, AutoModelForCausalLM
 import torch
 import json
-from datetime import datetime
 
 # Set Hugging Face Token for Authentication (ensure it's set in your environment)
 HUGGINGFACE_TOKEN = os.getenv("HUGGINGFACE_TOKEN")
@@ -14,7 +13,7 @@ tokenizer = LlamaTokenizer.from_pretrained(MODEL_NAME, token=HUGGINGFACE_TOKEN)
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_NAME,
     token=HUGGINGFACE_TOKEN,
-    device_map="cpu"  # Force CPU usage
+    device_map="cpu"
 )
 
 # Load Llama Guard for content moderation on CPU