Fairseq

Making Sentence Embeddings Robust to User-Generated Content
Lydia Nishimwe, Benoît Sagot, Rachel Bawden
Making Sentence Embeddings Robust to User-Generated Content
Your Fairseq-trained model might have more embedding parameters than it should.
How a bug in reading SentencePiece vocabulary files causes some Fairseq-trained models to have up to 3k extra parameters in the embedding layer.
Lydia Nishimwe
Last updated on Jun 4, 2024
Your Fairseq-trained model might have more embedding parameters than it should.