Update app.py

app.py

@@ -6,10 +6,12 @@ from threading import Thread
 import torch
 import spaces
 import gradio as gr
+from huggingface_hub import login
 from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, TextIteratorStreamer
 
 subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
 
+login(os.environ.get("HF_TOKEN"))
 MODEL_ID = os.environ.get("MODEL_ID")
 CHAT_TEMPLATE = os.environ.get("CHAT_TEMPLATE")
 MODEL_NAME = MODEL_ID.split("/")[-1]