Update app.py

app.py

@@ -8,7 +8,7 @@ assert (
 ), "LLaMA is now in HuggingFace's main branch.\nPlease reinstall it: pip uninstall transformers && pip install git+https://github.com/huggingface/transformers.git"
 from transformers import LlamaTokenizer, LlamaForCausalLM, GenerationConfig
 
-tokenizer = LlamaTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
+tokenizer = LlamaTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf", use_auth_token=True)
 
 BASE_MODEL = "meta-llama/Llama-2-7b-chat-hf"
 LORA_WEIGHTS = "Sparticle/llama-2-7b-japanese-lora"
@@ -30,6 +30,7 @@ if device == "cuda":
         load_in_8bit=False,
         torch_dtype=torch.float16,
         device_map="auto",
+        from_pretrained,
     )
     model = PeftModel.from_pretrained(
         model, LORA_WEIGHTS, torch_dtype=torch.float16, force_download=True
@@ -39,6 +40,7 @@ elif device == "mps":
         BASE_MODEL,
         device_map={"": device},
         torch_dtype=torch.float16,
+        from_pretrained,
     )
     model = PeftModel.from_pretrained(
         model,