sentence-transformers/msmarco-distilbert-base-v3

The Sentence Embedding Model is a distilroberta-base model from the sentence-transformers-repository . It was trained on the MS MARCO Passage Retrieval dataset: Given a search query, it finds the relevant passages . You can use the model directly from the model repository to compute sentence embeddings . The models used for all training queries similar to those of v.2 have been used for finding for passages similar to v.3 . If they received a low score, we saved them as hard: They got a high score from the bi-encoder, but a low-score from the (better cross-encoding) but a high,