allow load

app.py

@@ -5,8 +5,8 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 
 app = FastAPI()
 
-tokenizer = AutoTokenizer.from_pretrained("Intel/neural-chat-7b-v3-1", local_files_only=True)
-model = AutoModelForCausalLM.from_pretrained("Intel/neural-chat-7b-v3-1", local_files_only=True)
+tokenizer = AutoTokenizer.from_pretrained("Intel/neural-chat-7b-v3-1")
+model = AutoModelForCausalLM.from_pretrained("Intel/neural-chat-7b-v3-1")
 
 class ChatInput(BaseModel):
     system_input: str