Update app.py

app.py

@@ -45,9 +45,10 @@ model = AutoModelForCausalLM.from_pretrained(
     MODEL_ID,
     torch_dtype=torch.bfloat16,
     low_cpu_mem_usage=True,
-    trust_remote_code=True
+    trust_remote_code=True,
+    token=HF_TOKEN
 ).to(0)
-tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True, token=HF_TOKEN)
 model.eval()