the dir(jax_file)
output is mentioned above in my question part, the output of jax_file.__dict__
is as below:
jax_file.__dict__
{'_files': ['Transformer/encoder_norm/bias.npy', 'Transformer/encoder_norm/scale.npy', 'Transformer/encoderblock_0/LayerNorm_0/bias.npy', 'Transformer/encoderblock_0/LayerNorm_0/scale.npy', 'Transformer/encoderblock_0/LayerNorm_2/bias.npy', 'Transformer/encoderblock_0/LayerNorm_2/scale.npy', 'Transformer/encoderblock_0/MlpBlock_3/Dense_0/bias.npy', 'Transformer/encoderblock_0/MlpBlock_3/Dense_0/kernel.npy', 'Transformer/encoderblock_0/MlpBlock_3/Dense_1/bias.npy', 'Transformer/encoderblock_0/MlpBlock_3/Dense_1/kernel.npy', 'Transformer/encoderblock_0/MultiHeadDotProductAttention_1/key/bias.npy', 'Transformer/encoderblock_0/MultiHeadDotProductAttention_1/key/kernel.npy', 'Transformer/encoderblock_0/MultiHeadDotProductAttention_1/out/bias.npy', 'Transformer/encoderblock_0/MultiHeadDotProductAttention_1/out/kernel.npy', 'Transformer/encoderblock_0/MultiHeadDotProductAttention_1/query/bias.npy', 'Transformer/encoderblock_0/MultiHeadDotProductAttention_1/query/kernel.npy', 'Transformer/encoderblock_0/MultiHeadDotProductAttention_1/value/bias.npy', 'Transformer/encoderblock_0/MultiHeadDotProductAttention_1/value/kernel.npy', 'Transformer/encoderblock_1/LayerNorm_0/bias.npy', 'Transformer/encoderblock_1/LayerNorm_0/scale.npy', 'Transformer/encoderblock_1/LayerNorm_2/bias.npy', 'Transformer/encoderblock_1/LayerNorm_2/scale.npy', 'Transformer/encoderblock_1/MlpBlock_3/Dense_0/bias.npy', 'Transformer/encoderblock_1/MlpBlock_3/Dense_0/kernel.npy', 'Transformer/encoderblock_1/MlpBlock_3/Dense_1/bias.npy', 'Transformer/encoderblock_1/MlpBlock_3/Dense_1/kernel.npy', 'Transformer/encoderblock_1/MultiHeadDotProductAttention_1/key/bias.npy', 'Transformer/encoderblock_1/MultiHeadDotProductAttention_1/key/kernel.npy', 'Transformer/encoderblock_1/MultiHeadDotProductAttention_1/out/bias.npy', 'Transformer/encoderblock_1/MultiHeadDotProductAttention_1/out/kernel.npy', 'Transformer/encoderblock_1/MultiHeadDotProductAttention_1/query/bias.npy', 'Transformer/encoderblock_1/MultiHeadDotProductAttention_1/query/kernel.npy', 'Transformer/encoderblock_1/MultiHeadDotProductAttention_1/value/bias.npy', 'Transformer/encoderblock_1/MultiHeadDotProductAttention_1/value/kernel.npy', 'Transformer/encoderblock_10/LayerNorm_0/bias.npy', 'Transformer/encoderblock_10/LayerNorm_0/scale.npy', 'Transformer/encoderblock_10/LayerNorm_2/bias.npy', 'Transformer/encoderblock_10/LayerNorm_2/scale.npy', 'Transformer/encoderblock_10/MlpBlock_3/Dense_0/bias.npy', 'Transformer/encoderblock_10/MlpBlock_3/Dense_0/kernel.npy', 'Transformer/encoderblock_10/MlpBlock_3/Dense_1/bias.npy', 'Transformer/encoderblock_10/MlpBlock_3/Dense_1/kernel.npy', 'Transformer/encoderblock_10/MultiHeadDotProductAttention_1/key/bias.npy', 'Transformer/encoderblock_10/MultiHeadDotProductAttention_1/key/kernel.npy', 'Transformer/encoderblock_10/MultiHeadDotProductAttention_1/out/bias.npy', 'Transformer/encoderblock_10/MultiHeadDotProductAttention_1/out/kernel.npy', 'Transformer/encoderblock_10/MultiHeadDotProductAttention_1/query/bias.npy', 'Transformer/encoderblock_10/MultiHeadDotProductAttention_1/query/kernel.npy', 'Transformer/encoderblock_10/MultiHeadDotProductAttention_1/value/bias.npy', 'Transformer/encoderblock_10/MultiHeadDotProductAttention_1/value/kernel.npy', 'Transformer/encoderblock_11/LayerNorm_0/bias.npy', 'Transformer/encoderblock_11/LayerNorm_0/scale.npy', 'Transformer/encoderblock_11/LayerNorm_2/bias.npy', 'Transformer/encoderblock_11/LayerNorm_2/scale.npy', 'Transformer/encoderblock_11/MlpBlock_3/Dense_0/bias.npy', 'Transformer/encoderblock_11/MlpBlock_3/Dense_0/kernel.npy', 'Transformer/encoderblock_11/MlpBlock_3/Dense_1/bias.npy', 'Transformer/encoderblock_11/MlpBlock_3/Dense_1/kernel.npy', 'Transformer/encoderblock_11/MultiHeadDotProductAttention_1/key/bias.npy', 'Transformer/encoderblock_11/MultiHeadDotProductAttention_1/key/kernel.npy', 'Transformer/encoderblock_11/MultiHeadDotProductAttention_1/out/bias.npy', 'Transformer/encoderblock_11/MultiHeadDotProductAttention_1/out/kernel.npy', 'Transformer/encoderblock_11/MultiHeadDotProductAttention_1/query/bias.npy', 'Transformer/encoderblock_11/MultiHeadDotProductAttention_1/query/kernel.npy', 'Transformer/encoderblock_11/MultiHeadDotProductAttention_1/value/bias.npy', 'Transformer/encoderblock_11/MultiHeadDotProductAttention_1/value/kernel.npy', 'Transformer/encoderblock_2/LayerNorm_0/bias.npy', 'Transformer/encoderblock_2/LayerNorm_0/scale.npy', 'Transformer/encoderblock_2/LayerNorm_2/bias.npy', 'Transformer/encoderblock_2/LayerNorm_2/scale.npy', 'Transformer/encoderblock_2/MlpBlock_3/Dense_0/bias.npy', 'Transformer/encoderblock_2/MlpBlock_3/Dense_0/kernel.npy', 'Transformer/encoderblock_2/MlpBlock_3/Dense_1/bias.npy', 'Transformer/encoderblock_2/MlpBlock_3/Dense_1/kernel.npy', 'Transformer/encoderblock_2/MultiHeadDotProductAttention_1/key/bias.npy', 'Transformer/encoderblock_2/MultiHeadDotProductAttention_1/key/kernel.npy', 'Transformer/encoderblock_2/MultiHeadDotProductAttention_1/out/bias.npy', 'Transformer/encoderblock_2/MultiHeadDotProductAttention_1/out/kernel.npy', 'Transformer/encoderblock_2/MultiHeadDotProductAttention_1/query/bias.npy', 'Transformer/encoderblock_2/MultiHeadDotProductAttention_1/query/kernel.npy', 'Transformer/encoderblock_2/MultiHeadDotProductAttention_1/value/bias.npy', 'Transformer/encoderblock_2/MultiHeadDotProductAttention_1/value/kernel.npy', 'Transformer/encoderblock_3/LayerNorm_0/bias.npy', 'Transformer/encoderblock_3/LayerNorm_0/scale.npy', 'Transformer/encoderblock_3/LayerNorm_2/bias.npy', 'Transformer/encoderblock_3/LayerNorm_2/scale.npy', 'Transformer/encoderblock_3/MlpBlock_3/Dense_0/bias.npy', 'Transformer/encoderblock_3/MlpBlock_3/Dense_0/kernel.npy', 'Transformer/encoderblock_3/MlpBlock_3/Dense_1/bias.npy', 'Transformer/encoderblock_3/MlpBlock_3/Dense_1/kernel.npy', 'Transformer/encoderblock_3/MultiHeadDotProductAttention_1/key/bias.npy', 'Transformer/encoderblock_3/MultiHeadDotProductAttention_1/key/kernel.npy', 'Transformer/encoderblock_3/MultiHeadDotProductAttention_1/out/bias.npy', 'Transformer/encoderblock_3/MultiHeadDotProductAttention_1/out/kernel.npy', 'Transformer/encoderblock_3/MultiHeadDotProductAttention_1/query/bias.npy', 'Transformer/encoderblock_3/MultiHeadDotProductAttention_1/query/kernel.npy', 'Transformer/encoderblock_3/MultiHeadDotProductAttention_1/value/bias.npy', 'Transformer/encoderblock_3/MultiHeadDotProductAttention_1/value/kernel.npy', 'Transformer/encoderblock_4/LayerNorm_0/bias.npy', 'Transformer/encoderblock_4/LayerNorm_0/scale.npy', 'Transformer/encoderblock_4/LayerNorm_2/bias.npy', 'Transformer/encoderblock_4/LayerNorm_2/scale.npy', 'Transformer/encoderblock_4/MlpBlock_3/Dense_0/bias.npy', 'Transformer/encoderblock_4/MlpBlock_3/Dense_0/kernel.npy', 'Transformer/encoderblock_4/MlpBlock_3/Dense_1/bias.npy', 'Transformer/encoderblock_4/MlpBlock_3/Dense_1/kernel.npy', 'Transformer/encoderblock_4/MultiHeadDotProductAttention_1/key/bias.npy', 'Transformer/encoderblock_4/MultiHeadDotProductAttention_1/key/kernel.npy', 'Transformer/encoderblock_4/MultiHeadDotProductAttention_1/out/bias.npy', 'Transformer/encoderblock_4/MultiHeadDotProductAttention_1/out/kernel.npy', 'Transformer/encoderblock_4/MultiHeadDotProductAttention_1/query/bias.npy', 'Transformer/encoderblock_4/MultiHeadDotProductAttention_1/query/kernel.npy', 'Transformer/encoderblock_4/MultiHeadDotProductAttention_1/value/bias.npy', 'Transformer/encoderblock_4/MultiHeadDotProductAttention_1/value/kernel.npy', 'Transformer/encoderblock_5/LayerNorm_0/bias.npy', 'Transformer/encoderblock_5/LayerNorm_0/scale.npy', 'Transformer/encoderblock_5/LayerNorm_2/bias.npy', 'Transformer/encoderblock_5/LayerNorm_2/scale.npy', 'Transformer/encoderblock_5/MlpBlock_3/Dense_0/bias.npy', 'Transformer/encoderblock_5/MlpBlock_3/Dense_0/kernel.npy', 'Transformer/encoderblock_5/MlpBlock_3/Dense_1/bias.npy', 'Transformer/encoderblock_5/MlpBlock_3/Dense_1/kernel.npy', 'Transformer/encoderblock_5/MultiHeadDotProductAttention_1/key/bias.npy', 'Transformer/encoderblock_5/MultiHeadDotProductAttention_1/key/kernel.npy', 'Transformer/encoderblock_5/MultiHeadDotProductAttention_1/out/bias.npy', 'Transformer/encoderblock_5/MultiHeadDotProductAttention_1/out/kernel.npy', 'Transformer/encoderblock_5/MultiHeadDotProductAttention_1/query/bias.npy', 'Transformer/encoderblock_5/MultiHeadDotProductAttention_1/query/kernel.npy', 'Transformer/encoderblock_5/MultiHeadDotProductAttention_1/value/bias.npy', 'Transformer/encoderblock_5/MultiHeadDotProductAttention_1/value/kernel.npy', 'Transformer/encoderblock_6/LayerNorm_0/bias.npy', 'Transformer/encoderblock_6/LayerNorm_0/scale.npy', 'Transformer/encoderblock_6/LayerNorm_2/bias.npy', 'Transformer/encoderblock_6/LayerNorm_2/scale.npy', 'Transformer/encoderblock_6/MlpBlock_3/Dense_0/bias.npy', 'Transformer/encoderblock_6/MlpBlock_3/Dense_0/kernel.npy', 'Transformer/encoderblock_6/MlpBlock_3/Dense_1/bias.npy', 'Transformer/encoderblock_6/MlpBlock_3/Dense_1/kernel.npy', 'Transformer/encoderblock_6/MultiHeadDotProductAttention_1/key/bias.npy', 'Transformer/encoderblock_6/MultiHeadDotProductAttention_1/key/kernel.npy', 'Transformer/encoderblock_6/MultiHeadDotProductAttention_1/out/bias.npy', 'Transformer/encoderblock_6/MultiHeadDotProductAttention_1/out/kernel.npy', 'Transformer/encoderblock_6/MultiHeadDotProductAttention_1/query/bias.npy', 'Transformer/encoderblock_6/MultiHeadDotProductAttention_1/query/kernel.npy', 'Transformer/encoderblock_6/MultiHeadDotProductAttention_1/value/bias.npy', 'Transformer/encoderblock_6/MultiHeadDotProductAttention_1/value/kernel.npy', 'Transformer/encoderblock_7/LayerNorm_0/bias.npy', 'Transformer/encoderblock_7/LayerNorm_0/scale.npy', 'Transformer/encoderblock_7/LayerNorm_2/bias.npy', 'Transformer/encoderblock_7/LayerNorm_2/scale.npy', 'Transformer/encoderblock_7/MlpBlock_3/Dense_0/bias.npy', 'Transformer/encoderblock_7/MlpBlock_3/Dense_0/kernel.npy', 'Transformer/encoderblock_7/MlpBlock_3/Dense_1/bias.npy', 'Transformer/encoderblock_7/MlpBlock_3/Dense_1/kernel.npy', 'Transformer/encoderblock_7/MultiHeadDotProductAttention_1/key/bias.npy', 'Transformer/encoderblock_7/MultiHeadDotProductAttention_1/key/kernel.npy', 'Transformer/encoderblock_7/MultiHeadDotProductAttention_1/out/bias.npy', 'Transformer/encoderblock_7/MultiHeadDotProductAttention_1/out/kernel.npy', 'Transformer/encoderblock_7/MultiHeadDotProductAttention_1/query/bias.npy', 'Transformer/encoderblock_7/MultiHeadDotProductAttention_1/query/kernel.npy', 'Transformer/encoderblock_7/MultiHeadDotProductAttention_1/value/bias.npy', 'Transformer/encoderblock_7/MultiHeadDotProductAttention_1/value/kernel.npy', 'Transformer/encoderblock_8/LayerNorm_0/bias.npy', 'Transformer/encoderblock_8/LayerNorm_0/scale.npy', 'Transformer/encoderblock_8/LayerNorm_2/bias.npy', 'Transformer/encoderblock_8/LayerNorm_2/scale.npy', 'Transformer/encoderblock_8/MlpBlock_3/Dense_0/bias.npy', 'Transformer/encoderblock_8/MlpBlock_3/Dense_0/kernel.npy', 'Transformer/encoderblock_8/MlpBlock_3/Dense_1/bias.npy', 'Transformer/encoderblock_8/MlpBlock_3/Dense_1/kernel.npy', 'Transformer/encoderblock_8/MultiHeadDotProductAttention_1/key/bias.npy', 'Transformer/encoderblock_8/MultiHeadDotProductAttention_1/key/kernel.npy', 'Transformer/encoderblock_8/MultiHeadDotProductAttention_1/out/bias.npy', 'Transformer/encoderblock_8/MultiHeadDotProductAttention_1/out/kernel.npy', 'Transformer/encoderblock_8/MultiHeadDotProductAttention_1/query/bias.npy', 'Transformer/encoderblock_8/MultiHeadDotProductAttention_1/query/kernel.npy', 'Transformer/encoderblock_8/MultiHeadDotProductAttention_1/value/bias.npy', 'Transformer/encoderblock_8/MultiHeadDotProductAttention_1/value/kernel.npy', 'Transformer/encoderblock_9/LayerNorm_0/bias.npy', 'Transformer/encoderblock_9/LayerNorm_0/scale.npy', 'Transformer/encoderblock_9/LayerNorm_2/bias.npy', 'Transformer/encoderblock_9/LayerNorm_2/scale.npy', 'Transformer/encoderblock_9/MlpBlock_3/Dense_0/bias.npy', 'Transformer/encoderblock_9/MlpBlock_3/Dense_0/kernel.npy', 'Transformer/encoderblock_9/MlpBlock_3/Dense_1/bias.npy', 'Transformer/encoderblock_9/MlpBlock_3/Dense_1/kernel.npy', 'Transformer/encoderblock_9/MultiHeadDotProductAttention_1/key/bias.npy', 'Transformer/encoderblock_9/MultiHeadDotProductAttention_1/key/kernel.npy', 'Transformer/encoderblock_9/MultiHeadDotProductAttention_1/out/bias.npy', 'Transformer/encoderblock_9/MultiHeadDotProductAttention_1/out/kernel.npy', 'Transformer/encoderblock_9/MultiHeadDotProductAttention_1/query/bias.npy', 'Transformer/encoderblock_9/MultiHeadDotProductAttention_1/query/kernel.npy', 'Transformer/encoderblock_9/MultiHeadDotProductAttention_1/value/bias.npy', 'Transformer/encoderblock_9/MultiHeadDotProductAttention_1/value/kernel.npy', 'Transformer/posembed_input/pos_embedding.npy', 'cls.npy', 'embedding/bias.npy', 'embedding/kernel.npy', 'head/bias.npy', 'head/kernel.npy', 'pre_logits/bias.npy', 'pre_logits/kernel.npy'], 'files': ['Transformer/encoder_norm/bias', 'Transformer/encoder_norm/scale', 'Transformer/encoderblock_0/LayerNorm_0/bias', 'Transformer/encoderblock_0/LayerNorm_0/scale', 'Transformer/encoderblock_0/LayerNorm_2/bias', 'Transformer/encoderblock_0/LayerNorm_2/scale', 'Transformer/encoderblock_0/MlpBlock_3/Dense_0/bias', 'Transformer/encoderblock_0/MlpBlock_3/Dense_0/kernel', 'Transformer/encoderblock_0/MlpBlock_3/Dense_1/bias', 'Transformer/encoderblock_0/MlpBlock_3/Dense_1/kernel', 'Transformer/encoderblock_0/MultiHeadDotProductAttention_1/key/bias', 'Transformer/encoderblock_0/MultiHeadDotProductAttention_1/key/kernel', 'Transformer/encoderblock_0/MultiHeadDotProductAttention_1/out/bias', 'Transformer/encoderblock_0/MultiHeadDotProductAttention_1/out/kernel', 'Transformer/encoderblock_0/MultiHeadDotProductAttention_1/query/bias', 'Transformer/encoderblock_0/MultiHeadDotProductAttention_1/query/kernel', 'Transformer/encoderblock_0/MultiHeadDotProductAttention_1/value/bias', 'Transformer/encoderblock_0/MultiHeadDotProductAttention_1/value/kernel', 'Transformer/encoderblock_1/LayerNorm_0/bias', 'Transformer/encoderblock_1/LayerNorm_0/scale', 'Transformer/encoderblock_1/LayerNorm_2/bias', 'Transformer/encoderblock_1/LayerNorm_2/scale', 'Transformer/encoderblock_1/MlpBlock_3/Dense_0/bias', 'Transformer/encoderblock_1/MlpBlock_3/Dense_0/kernel', 'Transformer/encoderblock_1/MlpBlock_3/Dense_1/bias', 'Transformer/encoderblock_1/MlpBlock_3/Dense_1/kernel', 'Transformer/encoderblock_1/MultiHeadDotProductAttention_1/key/bias', 'Transformer/encoderblock_1/MultiHeadDotProductAttention_1/key/kernel', 'Transformer/encoderblock_1/MultiHeadDotProductAttention_1/out/bias', 'Transformer/encoderblock_1/MultiHeadDotProductAttention_1/out/kernel', 'Transformer/encoderblock_1/MultiHeadDotProductAttention_1/query/bias', 'Transformer/encoderblock_1/MultiHeadDotProductAttention_1/query/kernel', 'Transformer/encoderblock_1/MultiHeadDotProductAttention_1/value/bias', 'Transformer/encoderblock_1/MultiHeadDotProductAttention_1/value/kernel', 'Transformer/encoderblock_10/LayerNorm_0/bias', 'Transformer/encoderblock_10/LayerNorm_0/scale', 'Transformer/encoderblock_10/LayerNorm_2/bias', 'Transformer/encoderblock_10/LayerNorm_2/scale', 'Transformer/encoderblock_10/MlpBlock_3/Dense_0/bias', 'Transformer/encoderblock_10/MlpBlock_3/Dense_0/kernel', 'Transformer/encoderblock_10/MlpBlock_3/Dense_1/bias', 'Transformer/encoderblock_10/MlpBlock_3/Dense_1/kernel', 'Transformer/encoderblock_10/MultiHeadDotProductAttention_1/key/bias', 'Transformer/encoderblock_10/MultiHeadDotProductAttention_1/key/kernel', 'Transformer/encoderblock_10/MultiHeadDotProductAttention_1/out/bias', 'Transformer/encoderblock_10/MultiHeadDotProductAttention_1/out/kernel', 'Transformer/encoderblock_10/MultiHeadDotProductAttention_1/query/bias', 'Transformer/encoderblock_10/MultiHeadDotProductAttention_1/query/kernel', 'Transformer/encoderblock_10/MultiHeadDotProductAttention_1/value/bias', 'Transformer/encoderblock_10/MultiHeadDotProductAttention_1/value/kernel', 'Transformer/encoderblock_11/LayerNorm_0/bias', 'Transformer/encoderblock_11/LayerNorm_0/scale', 'Transformer/encoderblock_11/LayerNorm_2/bias', 'Transformer/encoderblock_11/LayerNorm_2/scale', 'Transformer/encoderblock_11/MlpBlock_3/Dense_0/bias', 'Transformer/encoderblock_11/MlpBlock_3/Dense_0/kernel', 'Transformer/encoderblock_11/MlpBlock_3/Dense_1/bias', 'Transformer/encoderblock_11/MlpBlock_3/Dense_1/kernel', 'Transformer/encoderblock_11/MultiHeadDotProductAttention_1/key/bias', 'Transformer/encoderblock_11/MultiHeadDotProductAttention_1/key/kernel', 'Transformer/encoderblock_11/MultiHeadDotProductAttention_1/out/bias', 'Transformer/encoderblock_11/MultiHeadDotProductAttention_1/out/kernel', 'Transformer/encoderblock_11/MultiHeadDotProductAttention_1/query/bias', 'Transformer/encoderblock_11/MultiHeadDotProductAttention_1/query/kernel', 'Transformer/encoderblock_11/MultiHeadDotProductAttention_1/value/bias', 'Transformer/encoderblock_11/MultiHeadDotProductAttention_1/value/kernel', 'Transformer/encoderblock_2/LayerNorm_0/bias', 'Transformer/encoderblock_2/LayerNorm_0/scale', 'Transformer/encoderblock_2/LayerNorm_2/bias', 'Transformer/encoderblock_2/LayerNorm_2/scale', 'Transformer/encoderblock_2/MlpBlock_3/Dense_0/bias', 'Transformer/encoderblock_2/MlpBlock_3/Dense_0/kernel', 'Transformer/encoderblock_2/MlpBlock_3/Dense_1/bias', 'Transformer/encoderblock_2/MlpBlock_3/Dense_1/kernel', 'Transformer/encoderblock_2/MultiHeadDotProductAttention_1/key/bias', 'Transformer/encoderblock_2/MultiHeadDotProductAttention_1/key/kernel', 'Transformer/encoderblock_2/MultiHeadDotProductAttention_1/out/bias', 'Transformer/encoderblock_2/MultiHeadDotProductAttention_1/out/kernel', 'Transformer/encoderblock_2/MultiHeadDotProductAttention_1/query/bias', 'Transformer/encoderblock_2/MultiHeadDotProductAttention_1/query/kernel', 'Transformer/encoderblock_2/MultiHeadDotProductAttention_1/value/bias', 'Transformer/encoderblock_2/MultiHeadDotProductAttention_1/value/kernel', 'Transformer/encoderblock_3/LayerNorm_0/bias', 'Transformer/encoderblock_3/LayerNorm_0/scale', 'Transformer/encoderblock_3/LayerNorm_2/bias', 'Transformer/encoderblock_3/LayerNorm_2/scale', 'Transformer/encoderblock_3/MlpBlock_3/Dense_0/bias', 'Transformer/encoderblock_3/MlpBlock_3/Dense_0/kernel', 'Transformer/encoderblock_3/MlpBlock_3/Dense_1/bias', 'Transformer/encoderblock_3/MlpBlock_3/Dense_1/kernel', 'Transformer/encoderblock_3/MultiHeadDotProductAttention_1/key/bias', 'Transformer/encoderblock_3/MultiHeadDotProductAttention_1/key/kernel', 'Transformer/encoderblock_3/MultiHeadDotProductAttention_1/out/bias', 'Transformer/encoderblock_3/MultiHeadDotProductAttention_1/out/kernel', 'Transformer/encoderblock_3/MultiHeadDotProductAttention_1/query/bias', 'Transformer/encoderblock_3/MultiHeadDotProductAttention_1/query/kernel', 'Transformer/encoderblock_3/MultiHeadDotProductAttention_1/value/bias', 'Transformer/encoderblock_3/MultiHeadDotProductAttention_1/value/kernel', 'Transformer/encoderblock_4/LayerNorm_0/bias', 'Transformer/encoderblock_4/LayerNorm_0/scale', 'Transformer/encoderblock_4/LayerNorm_2/bias', 'Transformer/encoderblock_4/LayerNorm_2/scale', 'Transformer/encoderblock_4/MlpBlock_3/Dense_0/bias', 'Transformer/encoderblock_4/MlpBlock_3/Dense_0/kernel', 'Transformer/encoderblock_4/MlpBlock_3/Dense_1/bias', 'Transformer/encoderblock_4/MlpBlock_3/Dense_1/kernel', 'Transformer/encoderblock_4/MultiHeadDotProductAttention_1/key/bias', 'Transformer/encoderblock_4/MultiHeadDotProductAttention_1/key/kernel', 'Transformer/encoderblock_4/MultiHeadDotProductAttention_1/out/bias', 'Transformer/encoderblock_4/MultiHeadDotProductAttention_1/out/kernel', 'Transformer/encoderblock_4/MultiHeadDotProductAttention_1/query/bias', 'Transformer/encoderblock_4/MultiHeadDotProductAttention_1/query/kernel', 'Transformer/encoderblock_4/MultiHeadDotProductAttention_1/value/bias', 'Transformer/encoderblock_4/MultiHeadDotProductAttention_1/value/kernel', 'Transformer/encoderblock_5/LayerNorm_0/bias', 'Transformer/encoderblock_5/LayerNorm_0/scale', 'Transformer/encoderblock_5/LayerNorm_2/bias', 'Transformer/encoderblock_5/LayerNorm_2/scale', 'Transformer/encoderblock_5/MlpBlock_3/Dense_0/bias', 'Transformer/encoderblock_5/MlpBlock_3/Dense_0/kernel', 'Transformer/encoderblock_5/MlpBlock_3/Dense_1/bias', 'Transformer/encoderblock_5/MlpBlock_3/Dense_1/kernel', 'Transformer/encoderblock_5/MultiHeadDotProductAttention_1/key/bias', 'Transformer/encoderblock_5/MultiHeadDotProductAttention_1/key/kernel', 'Transformer/encoderblock_5/MultiHeadDotProductAttention_1/out/bias', 'Transformer/encoderblock_5/MultiHeadDotProductAttention_1/out/kernel', 'Transformer/encoderblock_5/MultiHeadDotProductAttention_1/query/bias', 'Transformer/encoderblock_5/MultiHeadDotProductAttention_1/query/kernel', 'Transformer/encoderblock_5/MultiHeadDotProductAttention_1/value/bias', 'Transformer/encoderblock_5/MultiHeadDotProductAttention_1/value/kernel', 'Transformer/encoderblock_6/LayerNorm_0/bias', 'Transformer/encoderblock_6/LayerNorm_0/scale', 'Transformer/encoderblock_6/LayerNorm_2/bias', 'Transformer/encoderblock_6/LayerNorm_2/scale', 'Transformer/encoderblock_6/MlpBlock_3/Dense_0/bias', 'Transformer/encoderblock_6/MlpBlock_3/Dense_0/kernel', 'Transformer/encoderblock_6/MlpBlock_3/Dense_1/bias', 'Transformer/encoderblock_6/MlpBlock_3/Dense_1/kernel', 'Transformer/encoderblock_6/MultiHeadDotProductAttention_1/key/bias', 'Transformer/encoderblock_6/MultiHeadDotProductAttention_1/key/kernel', 'Transformer/encoderblock_6/MultiHeadDotProductAttention_1/out/bias', 'Transformer/encoderblock_6/MultiHeadDotProductAttention_1/out/kernel', 'Transformer/encoderblock_6/MultiHeadDotProductAttention_1/query/bias', 'Transformer/encoderblock_6/MultiHeadDotProductAttention_1/query/kernel', 'Transformer/encoderblock_6/MultiHeadDotProductAttention_1/value/bias', 'Transformer/encoderblock_6/MultiHeadDotProductAttention_1/value/kernel', 'Transformer/encoderblock_7/LayerNorm_0/bias', 'Transformer/encoderblock_7/LayerNorm_0/scale', 'Transformer/encoderblock_7/LayerNorm_2/bias', 'Transformer/encoderblock_7/LayerNorm_2/scale', 'Transformer/encoderblock_7/MlpBlock_3/Dense_0/bias', 'Transformer/encoderblock_7/MlpBlock_3/Dense_0/kernel', 'Transformer/encoderblock_7/MlpBlock_3/Dense_1/bias', 'Transformer/encoderblock_7/MlpBlock_3/Dense_1/kernel', 'Transformer/encoderblock_7/MultiHeadDotProductAttention_1/key/bias', 'Transformer/encoderblock_7/MultiHeadDotProductAttention_1/key/kernel', 'Transformer/encoderblock_7/MultiHeadDotProductAttention_1/out/bias', 'Transformer/encoderblock_7/MultiHeadDotProductAttention_1/out/kernel', 'Transformer/encoderblock_7/MultiHeadDotProductAttention_1/query/bias', 'Transformer/encoderblock_7/MultiHeadDotProductAttention_1/query/kernel', 'Transformer/encoderblock_7/MultiHeadDotProductAttention_1/value/bias', 'Transformer/encoderblock_7/MultiHeadDotProductAttention_1/value/kernel', 'Transformer/encoderblock_8/LayerNorm_0/bias', 'Transformer/encoderblock_8/LayerNorm_0/scale', 'Transformer/encoderblock_8/LayerNorm_2/bias', 'Transformer/encoderblock_8/LayerNorm_2/scale', 'Transformer/encoderblock_8/MlpBlock_3/Dense_0/bias', 'Transformer/encoderblock_8/MlpBlock_3/Dense_0/kernel', 'Transformer/encoderblock_8/MlpBlock_3/Dense_1/bias', 'Transformer/encoderblock_8/MlpBlock_3/Dense_1/kernel', 'Transformer/encoderblock_8/MultiHeadDotProductAttention_1/key/bias', 'Transformer/encoderblock_8/MultiHeadDotProductAttention_1/key/kernel', 'Transformer/encoderblock_8/MultiHeadDotProductAttention_1/out/bias', 'Transformer/encoderblock_8/MultiHeadDotProductAttention_1/out/kernel', 'Transformer/encoderblock_8/MultiHeadDotProductAttention_1/query/bias', 'Transformer/encoderblock_8/MultiHeadDotProductAttention_1/query/kernel', 'Transformer/encoderblock_8/MultiHeadDotProductAttention_1/value/bias', 'Transformer/encoderblock_8/MultiHeadDotProductAttention_1/value/kernel', 'Transformer/encoderblock_9/LayerNorm_0/bias', 'Transformer/encoderblock_9/LayerNorm_0/scale', 'Transformer/encoderblock_9/LayerNorm_2/bias', 'Transformer/encoderblock_9/LayerNorm_2/scale', 'Transformer/encoderblock_9/MlpBlock_3/Dense_0/bias', 'Transformer/encoderblock_9/MlpBlock_3/Dense_0/kernel', 'Transformer/encoderblock_9/MlpBlock_3/Dense_1/bias', 'Transformer/encoderblock_9/MlpBlock_3/Dense_1/kernel', 'Transformer/encoderblock_9/MultiHeadDotProductAttention_1/key/bias', 'Transformer/encoderblock_9/MultiHeadDotProductAttention_1/key/kernel', 'Transformer/encoderblock_9/MultiHeadDotProductAttention_1/out/bias', 'Transformer/encoderblock_9/MultiHeadDotProductAttention_1/out/kernel', 'Transformer/encoderblock_9/MultiHeadDotProductAttention_1/query/bias', 'Transformer/encoderblock_9/MultiHeadDotProductAttention_1/query/kernel', 'Transformer/encoderblock_9/MultiHeadDotProductAttention_1/value/bias', 'Transformer/encoderblock_9/MultiHeadDotProductAttention_1/value/kernel', 'Transformer/posembed_input/pos_embedding', 'cls', 'embedding/bias', 'embedding/kernel', 'head/bias', 'head/kernel', 'pre_logits/bias', 'pre_logits/kernel'], 'allow_pickle': False, 'pickle_kwargs': {'encoding': 'ASCII', 'fix_imports': True}, 'zip': <zipfile.ZipFile file=<_io.BufferedReader name='ViT-B_16_imagenet21k.npz'> mode='r'>, 'f': <numpy.lib.npyio.BagObj object at 0x7f86359bd790>, 'fid': <_io.BufferedReader name='ViT-B_16_imagenet21k.npz'>}