Update app.py

app.py

@@ -1,9 +1,15 @@
 import gradio as gr
 from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer
+import os
+
+
+# Retrieve the token from environment variables
+huggingface_token = os.getenv('LLAMA_ACCES_TOKEN')
+
+# Use the token with from_pretrained
+tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat", use_auth_token=huggingface_token)
+model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-chat", use_auth_token=huggingface_token)
 
-# Load your model and tokenizer
-tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat")
-model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-chat")
 
 # Load a content moderation pipeline
 moderation_pipeline = pipeline("text-classification", model="typeform/mobilebert-uncased-mnli")