sentence-transformers/ce-ms-marco-electra-base

The model can be used for Information Retrieval: Given a query, encode the query will all possible passages (e.g. retrieved with ElasticSearch) Then sort the passages in a decreasing order . The training code is available here: SBERT.net Training MS Marco. The model was trained on MS Marco Passage Ranking task . Pre-trained models are pre-trained on the TREC Deep Learning 2019 and the MSMarco Passage Reranking dataset . The model is based on a V100 GPU, with the fast tokenizer based on Rust being replaced by the standard Python tokenizer from Huggingface. A bottleneck for smaller models is the standard python tokenizer, which can be,