import tensorflow as tf
from tensorflow.python.training import checkpoint_utils as cp
cp.list_variables('./model.ckpt-12520')
Running the above snippet gives the following output
[('Variable', []), ('decoder/attention_wrapper/attention_layer/kernel', [600, 300]), ('decoder/attention_wrapper/attention_layer/kernel/Adam', [600, 300]), ('decoder/attention_wrapper/attention_layer/kernel/Adam_1', [600, 300]), ('decoder/attention_wrapper/bahdanau_attention/attention_b', [300]), ('decoder/attention_wrapper/bahdanau_attention/attention_b/Adam', [300]), ('decoder/attention_wrapper/bahdanau_attention/attention_b/Adam_1', [300]), ('decoder/attention_wrapper/bahdanau_attention/attention_g', []), ('decoder/attention_wrapper/bahdanau_attention/attention_g/Adam', []), ('decoder/attention_wrapper/bahdanau_attention/attention_g/Adam_1', []), ('decoder/attention_wrapper/bahdanau_attention/attention_v', [300]), ('decoder/attention_wrapper/bahdanau_attention/attention_v/Adam', [300]), ('decoder/attention_wrapper/bahdanau_attention/attention_v/Adam_1', [300]), ('decoder/attention_wrapper/bahdanau_attention/query_layer/kernel', [300, 300]), ('decoder/attention_wrapper/bahdanau_attention/query_layer/kernel/Adam', [300, 300]), ('decoder/attention_wrapper/bahdanau_attention/query_layer/kernel/Adam_1', [300, 300]), ('decoder/attention_wrapper/basic_lstm_cell/bias', [1200]), ('decoder/attention_wrapper/basic_lstm_cell/bias/Adam', [1200]), ('decoder/attention_wrapper/basic_lstm_cell/bias/Adam_1', [1200]), ('decoder/attention_wrapper/basic_lstm_cell/kernel', [900, 1200]), ('decoder/attention_wrapper/basic_lstm_cell/kernel/Adam', [900, 1200]), ('decoder/attention_wrapper/basic_lstm_cell/kernel/Adam_1', [900, 1200]), ('decoder/dense/kernel', [300, 49018]), ('decoder/dense/kernel/Adam', [300, 49018]), ('decoder/dense/kernel/Adam_1', [300, 49018]), ('decoder/memory_layer/kernel', [300, 300]), ('decoder/memory_layer/kernel/Adam', [300, 300]), ('decoder/memory_layer/kernel/Adam_1', [300, 300]), ('embeddings', [49018, 300]), ('embeddings/Adam', [49018, 300]), ('embeddings/Adam_1', [49018, 300]), ('loss/beta1_power', []), ('loss/beta2_power', []), ('stack_bidirectional_rnn/cell_0/bidirectional_rnn/bw/basic_lstm_cell/bias', [600]), ('stack_bidirectional_rnn/cell_0/bidirectional_rnn/bw/basic_lstm_cell/bias/Adam', [600]), ('stack_bidirectional_rnn/cell_0/bidirectional_rnn/bw/basic_lstm_cell/bias/Adam_1', [600]), ('stack_bidirectional_rnn/cell_0/bidirectional_rnn/bw/basic_lstm_cell/kernel', [450, 600]), ('stack_bidirectional_rnn/cell_0/bidirectional_rnn/bw/basic_lstm_cell/kernel/Adam', [450, 600]), ('stack_bidirectional_rnn/cell_0/bidirectional_rnn/bw/basic_lstm_cell/kernel/Adam_1', [450, 600]), ('stack_bidirectional_rnn/cell_0/bidirectional_rnn/fw/basic_lstm_cell/bias', [600]), ('stack_bidirectional_rnn/cell_0/bidirectional_rnn/fw/basic_lstm_cell/bias/Adam', [600]), ('stack_bidirectional_rnn/cell_0/bidirectional_rnn/fw/basic_lstm_cell/bias/Adam_1', [600]), ('stack_bidirectional_rnn/cell_0/bidirectional_rnn/fw/basic_lstm_cell/kernel', [450, 600]), ('stack_bidirectional_rnn/cell_0/bidirectional_rnn/fw/basic_lstm_cell/kernel/Adam', [450, 600]), ('stack_bidirectional_rnn/cell_0/bidirectional_rnn/fw/basic_lstm_cell/kernel/Adam_1', [450, 600]), ('stack_bidirectional_rnn/cell_1/bidirectional_rnn/bw/basic_lstm_cell/bias', [600]), ('stack_bidirectional_rnn/cell_1/bidirectional_rnn/bw/basic_lstm_cell/bias/Adam', [600]), ('stack_bidirectional_rnn/cell_1/bidirectional_rnn/bw/basic_lstm_cell/bias/Adam_1', [600]), ('stack_bidirectional_rnn/cell_1/bidirectional_rnn/bw/basic_lstm_cell/kernel', [450, 600]), ('stack_bidirectional_rnn/cell_1/bidirectional_rnn/bw/basic_lstm_cell/kernel/Adam', [450, 600]), ('stack_bidirectional_rnn/cell_1/bidirectional_rnn/bw/basic_lstm_cell/kernel/Adam_1', [450, 600]), ('stack_bidirectional_rnn/cell_1/bidirectional_rnn/fw/basic_lstm_cell/bias', [600]), ('stack_bidirectional_rnn/cell_1/bidirectional_rnn/fw/basic_lstm_cell/bias/Adam', [600]), ('stack_bidirectional_rnn/cell_1/bidirectional_rnn/fw/basic_lstm_cell/bias/Adam_1', [600]), ('stack_bidirectional_rnn/cell_1/bidirectional_rnn/fw/basic_lstm_cell/kernel', [450, 600]), ('stack_bidirectional_rnn/cell_1/bidirectional_rnn/fw/basic_lstm_cell/kernel/Adam', [450, 600]), ('stack_bidirectional_rnn/cell_1/bidirectional_rnn/fw/basic_lstm_cell/kernel/Adam_1', [450, 600])]
I realised that the embeddings variable is storing the word embeddings which is accounting for the increase in size of those files
cp.load_variable('./model.ckpt-12520', 'embeddings')