> encoder-only models add up to over a billion downloads per month, nearly three times more than decoder-only models
This is partially because people using decoders aren’t using huggingface at all (they would use an API call) but also because encoders are the unsung heroes of most serious ML applications.
If you want to do any ranking, recommendation, RAG, etc it will probably require an encoder. And typically that meant something in the BERT/RoBERTa/ALBERT family. So this is huge.
This is partially because people using decoders aren’t using huggingface at all (they would use an API call) but also because encoders are the unsung heroes of most serious ML applications.
If you want to do any ranking, recommendation, RAG, etc it will probably require an encoder. And typically that meant something in the BERT/RoBERTa/ALBERT family. So this is huge.