Update app.py

app.py

@@ -1,11 +1,15 @@
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import gradio as gr
+import os
+
+HF_TOKEN = os.getenv("HF_TOKEN")  # Read token from environment variable 
+login(token=HF_TOKEN) 
 
 # Load Llama-2 model
 model_name = "meta-llama/Llama-2-7b-chat-hf"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=True)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto", use_auth_token=True)
 
 # Define personalities
 personalities = {