Update app.py

app.py

@@ -10,23 +10,23 @@ For more information on `huggingface_hub` Inference API support, please check th
 """
 #client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 from llama_rope_scaled_monkey_patch import replace_llama_rope_with_scaled_rope
-        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"
 model = transformers.AutoModelForCausalLM.from_pretrained(
-                            base_model,
-                            torch_dtype=torch.float16,
-                            cache_dir=cache_dir,
-                            device_map="auto",
-                    )
+            base_model,
+            torch_dtype=torch.float16,
+            cache_dir=cache_dir,
+            device_map="auto",
+        )
 
 model = PeftModel.from_pretrained(
-                    model,
-                    lora_weights,
-                    device_map="auto",
-                    cache_dir=cache_dir,
-                    torch_dtype=torch.float16,
-                )
+            model,
+            lora_weights,
+            device_map="auto",
+            cache_dir=cache_dir,
+            torch_dtype=torch.float16,
+        )
 tokenizer =  AutoTokenizer.from_pretrained(base_model,use_fast=False,cache_dir=cache_dir)
 tokenizer.pad_token = tokenizer.unk_token
 model.eval()