sentence-transformers

Sentence Transformers is a framework for computing and training embeddings with state-of-the-art embedding and reranker models. With a Sentence Transformer you can create embeddings, with a Cross-Encoder (reranker) similarity scores, with a Sparse Encoder sparse embeddings, and with a Multi-Vector Encoder ColBERT-style token embeddings. Hugging Face hosts more than 15,000 pretrained models. You can also train and fine-tune your own embedding and reranker models.

• Compute sentence embeddings (Sentence Transformer)
• Cross-Encoder reranking
• Sparse Encoder sparse embeddings
• Multi-Vector Encoder (ColBERT-style)
• 15,000+ pretrained models
• Train and fine-tune embedding and reranker models
• ONNX and OpenVINO inference acceleration

Open source (free, weights/code released)

Released free under an open-source license with no extra cost for self-hosting (usage-based pricing when offered as a cloud API)

Estimate based on AI knowledge - please verify on the official site

• One of 60 AI tools in the Foundation Models field.
• Connected to 5 other tools — #16 in its field.