The model obtained after fine-tuning, how can it be used for inference?

[RuipingWang1986]

Hello, I have fine-tuned the pretrained model imagenet21k_ViT-B_16.npz using the command python -m vit_jax.main --workdir=/tmp/vit-$(date +%s) \ --config=$(pwd)/vit_jax/configs/vit.py:b16,cifar10 \ --config.pretrained_dir='gs://vit_models/imagenet21k', and the fine-tuned results have been saved to a folder named vit-44527685. However, there is no .npz file in this folder, and I also don’t know how to use the model I obtained after fine-tuning for inference services to verify the effectiveness of the fine-tuning. Could you please help me figure out where the problem lies?