Update app.py

app.py

@@ -24,8 +24,8 @@ HF_TOKEN = os.getenv("HF_TOKEN")  # Load from Render environment variable
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
-tokenizer = AutoTokenizer.from_pretrained(REPO_NAME, token=HF_TOKEN)
-#tokenizer = LlamaTokenizer.from_pretrained(REPO_NAME, use_auth_token=HF_TOKEN)
+#tokenizer = AutoTokenizer.from_pretrained(REPO_NAME, token=HF_TOKEN)
+tokenizer = LlamaTokenizer.from_pretrained(REPO_NAME, use_auth_token=HF_TOKEN)
 
 model = AutoModelForCausalLM.from_pretrained(
     REPO_NAME,