Update app.py

app.py

@@ -6,6 +6,9 @@ import gradio as gr
 import spaces
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+import os
+
+HF_TOKEN = os.environ.get("HF_TOKEN", None)
 
 MAX_MAX_NEW_TOKENS = 4096
 DEFAULT_MAX_NEW_TOKENS = 2048
@@ -23,8 +26,8 @@ if not torch.cuda.is_available():
 if torch.cuda.is_available():
     model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
     # model_id = "mistralai/Mistral-7B-Instruct-v0.2"
-    model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto",load_in_4bit=True)
-    tokenizer = AutoTokenizer.from_pretrained(model_id)
+    model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto",load_in_4bit=True, token=HF_TOKEN)
+    tokenizer = AutoTokenizer.from_pretrained(model_id, token=HF_TOKEN)
     tokenizer.use_default_system_prompt = False