Update app.py

app.py

@@ -21,8 +21,8 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 if torch.cuda.is_available():
     model_id = "Rijgersberg/GEITje-7B-chat"
-    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
-    tokenizer = AutoTokenizer.from_pretrained(model_id)
+    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto", token=HF_TOKEN)
+    tokenizer = AutoTokenizer.from_pretrained(model_id, token=HF_TOKEN)
 
 
 @spaces.GPU