issues
search
lassl
/
lassl
Easy Language Model Pretraining leveraging Huggingface's Transformers and Datasets
Apache License 2.0
127
stars
14
forks
source link
Refactor collator, tokenizer-training for ul2, t5
#104
Open
wavy-jung
opened
2 years ago
wavy-jung
commented
2 years ago
TODO
ul2, t5 collator 로직 개선
ul2 토크나이저 학습 시 sentinel tokens 옵션 수정
cc: @seopbo @DaehanKim
TODO
cc: @seopbo @DaehanKim