Update app.py

app.py

@@ -47,8 +47,12 @@ h1 {
 """
 
 # Load the tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-2b-jpn-it", token=TOKEN, torch_dtype=torch.bfloat16)
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2-2b-jpn-it", token=TOKEN, torch_dtype=torch.bfloat16,device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-2b-jpn-it")
+model = AutoModelForCausalLM.from_pretrained(
+    "google/gemma-2-2b-jpn-it",
+    device_map="auto",
+    torch_dtype=torch.bfloat16,
+)
 
 @spaces.GPU()
 def chat_llama3_8b(message: str,