princeton-nlp / SimCSE

[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

drpout

riyajatar37003 opened this issue · comments

Hi,

where exactly dropout is being applied ? can anyone point to code/file.

thanks

Hi,

We reuse the dropouts implemented by Huggingface's transformers, which are applied to attention blocks and hidden states of each transformer layer. See modeling_bert.py and modeling_roberta.py from transformers' source code for details.

Thanks got it.