Update app.py

app.py

@@ -8,7 +8,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStream
 from threading import Thread
 import torch
 
-TOKEN=os.environ["TOKEN"]
+HF_TOKEN=os.environ["TOKEN"]
 
 DESCRIPTION = '''
 <div>
@@ -47,11 +47,12 @@ h1 {
 """
 
 # Load the tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-2b-jpn-it")
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-2b-jpn-it",token=HF_TOKEN)
 model = AutoModelForCausalLM.from_pretrained(
     "google/gemma-2-2b-jpn-it",
     device_map="auto",
     torch_dtype=torch.bfloat16,
+    token=HF_TOKEN
 )
 
 @spaces.GPU()