Maze navigation with MLM-U

Large Concept Models: Language modeling in a sentence representation space

PyTorch implementation for HyperMixing, a linear-time token-mixing technique used in HyperMixer architecture

triple-encoders is a library for contextualizing distributed Sentence Transformers representations.

Cramming the training of a (BERT-type) language model into limited compute.

A PyTorch-based Speech Toolkit

Towards Lossless Encoding of Sentences

Code for ICLR 2019 paper 'CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model'

A python tool for evaluating the quality of sentence embeddings.

End-2-end multi-label classification in python