Update app.py

app.py

@@ -8,7 +8,7 @@ import gradio as gr
 import spaces
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
-
+from huggingface_hub import login
 MAX_MAX_NEW_TOKENS = 2048
 DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
@@ -38,6 +38,8 @@ if not torch.cuda.is_available():
 
 
 if torch.cuda.is_available():
+    # Login to Hugging Face
+    login(token=os.getenv("HUGGINGFACE_HUB_TOKEN"))
     model_id = "Fugaku-LLM/Fugaku-LLM-13B-instruct"
     model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", load_in_4bit=True)
     tokenizer = AutoTokenizer.from_pretrained(model_id)