Update app.py

app.py

@@ -11,7 +11,7 @@ from transformers import LlamaTokenizer, LlamaForCausalLM, GenerationConfig
 tokenizer = LlamaTokenizer.from_pretrained("daryl149/llama-2-7b-chat-hf")
 
 BASE_MODEL = "daryl149/llama-2-7b-chat-hf"
-LORA_WEIGHTS = "Sparticle/llama-2-7b-japanese-lora"
+LORA_WEIGHTS = "Sparticle/llama-2-7b-chat-japanese-lora"
 
 if torch.cuda.is_available():
     device = "cuda"