Sequence-Labeling-Early-Exit
Sequence-Labeling-Early-Exit copied to clipboard
Code for ACL 2021 paper: Accelerating BERT Inference for Sequence Labeling via Early-Exit
Results
2
Sequence-Labeling-Early-Exit issues
Sort by
recently updated
recently updated
newest added
Hi @LeeSureman , I am a bit confused with the modeling_bert_ee code. If the training mode is 'joint_sample_copy' as in further_train stage: The loss will computed in the if branch...
An error happened in load_data_.py, line 231, 'yangjie_rich_pretrain_bigram_path' is not defined. But in paths.py, this variable is not mentioned. And I also want to know which dataset in the paths.py...