huggingface/sentence-transformers
State-of-the-Art Embeddings, Retrieval, and Reranking
https://skillcdn.ai/gh/huggingface/sentence-transformers내 AI에 이 주소를 연결하면 이 스킬들을 쓸 수 있어요. 연결 방법 보기
- 미확인
- 기본 브랜치
main - 커밋
4a3b5cd - 라이선스
Apache-2.0
저장소 둘러보기
스킬과 문서의 원문에서 찾습니다. 화면용 번역은 검색되지 않아요.
문서
- MS MARCO Cross-EncodersMS MARCO is a large scale information retrieval corpus that was created based on real user search queries using Bing search engine. The provided models can be used for semantic search, i.e., given ke…docs/pretrained-models/ce-msmarco.md
- DPR-ModelsIn Dense Passage Retrieval for Open-Domain Question Answering Karpukhin et al. trained models based on Google's Natural Questions dataset:docs/pretrained-models/dpr.md
- MSMARCO ModelsMS MARCO is a large scale information retrieval corpus that was created based on real user search queries using Bing search engine. The provided models can be used for semantic search, i.e., given ke…docs/pretrained-models/msmarco-v1.md
- MSMARCO Models (Version 2)MS MARCO is a large scale information retrieval corpus that was created based on real user search queries using Bing search engine. The provided models can be used for semantic search, i.e., given ke…docs/pretrained-models/msmarco-v2.md
- MSMARCO ModelsMS MARCO is a large scale information retrieval corpus that was created based on real user search queries using Bing search engine. The provided models can be used for semantic search, i.e., given ke…docs/pretrained-models/msmarco-v3.md
- MSMARCO ModelsMS MARCO is a large scale information retrieval corpus that was created based on real user search queries using Bing search engine. The provided models can be used for semantic search, i.e., given ke…docs/pretrained-models/msmarco-v5.md
- NLI ModelsConneau et al., 2017, show in the InferSent-Paper (Supervised Learning of Universal Sentence Representations from Natural Language Inference Data) that training on Natural Language Inference (NLI) da…docs/pretrained-models/nli-models.md
- Natural Questions ModelsGoogle's Natural Questions dataset consists of about 100k real search queries from Google with the respective, relevant passage from Wikipedia. Models trained on this dataset work well for question-a…docs/pretrained-models/nq-v1.md
- STS ModelsThe models were first trained on NLI data, then we fine-tuned them on the STS benchmark dataset (docs, dataset). This generate sentence embeddings that are especially suitable to measure the semantic…docs/pretrained-models/sts-models.md
- Wikipedia Sections ModelsThe wikipedia-sections-models implement the idea from Ein Dor et al., 2018, Learning Thematic Similarity Metric Using Triplet Networks.docs/pretrained-models/wikipedia-sections-models.md