Update app.py

app.py

@@ -2,12 +2,12 @@ import gradio as gr
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 import os
- 
+
 # Load model and tokenizer with the token from environment variables
 model_name = "meta-llama/Llama-2-7b-hf"
 token = os.getenv("HUGGINGFACE_TOKEN")  # Get token from environment
-tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=token)
-model = AutoModelForCausalLM.from_pretrained(model_name, use_auth_token=token, torch_dtype=torch.float16)
+tokenizer = AutoTokenizer.from_pretrained(model_name, token=token)
+model = AutoModelForCausalLM.from_pretrained(model_name, token=token, torch_dtype=torch.float16)
 model = model.to("cuda" if torch.cuda.is_available() else "cpu")
 
 # Function to generate responses