Update app.py

app.py

@@ -11,10 +11,9 @@ MAX_MAX_NEW_TOKENS = 2048
 DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
-
 #if torch.cuda.is_available():
 model_id = "meta-llama/Llama-2-7b-chat-hf"
-model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, trust_remote_code=True, token=HF_TOKEN, device_map="auto")
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 tokenizer.use_default_system_prompt = False