git clone <https://github.com/cgmhaicenter/exBERT>
pip install torch transformers tqdm numpy
python Pretraining.py -e 1
-b 256
-sp path_to_storage
-dv 0 1 2 3 -lr 1e-04
-str exBERT
-config path_to_config_file_of_the_OFF_THE_SHELF_MODEL ./config_and_vocab/exBERT/bert_config_ex_s3.json
-vocab ./config_and_vocab/exBERT/exBERT_vocab.txt
-pm_p path_to_state_dict_of_the_OFF_THE_SHELF_MODEL
-dp path_to_your_training_data
-ls 128
-p 1
path_to_config_file_of_the_OFF_THE_SHELF_MODEL
없음아래와 같이 기존 모델인 beomi/kcbert-base
로 교체해주려고 함.
python Pretraining.py -e 1 \\
-b 256 \\
-sp path_to_storage \\
-dv 0 1 2 3 -lr 1e-04 \\
-str exBERT \\
-config **beomi/kcbert-base** ./config_and_vocab/exBERT/bert_config_ex_s3.json \\
-vocab ./config_and_vocab/exBERT/exBERT_vocab.txt \\
-pm_p **beomi/kcbert-base** \\
-dp path_to_your_training_data \\
-ls 128 \\
-p 1