Update app.py

app.py

@@ -1,4 +1,5 @@
 import torch
+import os
 
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 import gradio as gr
@@ -28,10 +29,11 @@ END_MESSAGE = """
 
 device = "cuda" # for GPU usage or "cpu" for CPU usage
 
-tokenizer = AutoTokenizer.from_pretrained(MODEL)
+tokenizer = AutoTokenizer.from_pretrained(MODEL, token=os.getenv("HF_TOKEN"))
 model = AutoModelForCausalLM.from_pretrained(
     MODEL,
     torch_dtype=torch.bfloat16,
+    token=os.getenv("HF_TOKEN")
 ).to(device)
 
 model = torch.compile(model)