tomaarsen
@tomaarsen
Sentence Transformers Lead, SetFit & NLTK maintainer
Machine Learning Engineer at 🤗 Hugging Face
加入 December 2023
482 正在关注 4.9K 粉丝
At 1400x cheaper, I know I'm sticking to embeddings (dense, sparse, multi-vector), plus hybrid (incl. bm25) and rerankers.
Perhaps I'd even use listwise cross-encoders, they seem interesting.
