Confusing the Part of ''Prepare Pre-train Data'' in Readme.

thunlp / ERNIE

Source code and dataset for ACL 2019 paper "ERNIE: Enhanced Language Representation with Informative Entities"

MIT License

1.41k stars 267 forks source link

Confusing the Part of ''Prepare Pre-train Data'' in Readme. #58

Closed scuhz closed 4 years ago

scuhz commented 4 years ago

python3 code/run_pretrain.py --do_train --data_dir pretrain_data/merge --bert_model ernie_base --output_dir pretrain_out/ --task_name pretrain --fp16 --max_seq_length 256 I think the value of the '--bert_model' is 'bert_base_uncased' rather 'ernie_base'?

leileilin commented 2 years ago

python3 code/run_pretrain.py --do_train --data_dir pretrain_data/merge --bert_model ernie_base --output_dir pretrain_out/ --task_name pretrain --fp16 --max_seq_length 256 I think the value of the '--bert_model' is 'bert_base_uncased' rather 'ernie_base'?

so is ernie_base or bert_base_uncased?