Update app.py

app.py

@@ -13,6 +13,7 @@ from llama_rope_scaled_monkey_patch import replace_llama_rope_with_scaled_rope
 replace_llama_rope_with_scaled_rope()
 base_model = "Neko-Institute-of-Science/LLaMA-65B-HF"
 lora_weights = "adapter_config.json"
+cache_dir = ""
 model = transformers.AutoModelForCausalLM.from_pretrained(
             base_model,
             torch_dtype=torch.float16,