Sentence Transformers
Sentence Transformers is a Python roof developed to calculate and train embedding, retrieval, and reranking models for texts. The roof allows you to generate text representations using the Sentence Transformer, Cross-Encoder, Sparse Encoder and Multi-Vector Encoder models. It provides access to thousands of pre-trained models offered on Hugging Face and allows you to train or fine-tune your own custom models.
UKPLab · Translation & NLP
Common commercial products in this category: Google Translate, DeepL, Microsoft Translator
- You calculate embedding for texts using pre-trained models
- Calculate similarity scores between cross-Encoder models and texts
- You train or fine-tune your own custom embedding and reranker models.
- ↓ NegativeHacker News
Show HN: ColBERT Build from Sentence Transformers
“Hi, there is a single loss right now, but I plan to add some Sentence Transformers losses. ColBERT is slow as a retriever, but is quite efficient as a Ranker on GPU (way faster than cross-encoder). I plan to release pre-trained checkpoints on HuggingFace with benchmarks using…”