Embeddings
MinishLab/model2vec๐ฅ active
Fast State-of-the-Art Static Embeddings
๐ง Natural Language Processing
PythonMITupdated Sep 21, 2026
Tools for shrinking fastText models (in gensim format)
$ git clone https://github.com/avidale/compress-fasttext.gitFast State-of-the-Art Static Embeddings
Spanish word embeddings computed with different methods and from different corpora
dna2vec: Consistent vector representations of variable-length k-mers
Lbl2Vec learns jointly embedded label, document and word vectors to retrieve documents with predefined topics from an unlabeled document corpus.
Topic Modelling for Humans
A very simple framework for state-of-the-art Natural Language Processing (NLP)
Data from GitHub ยท snapshot Sep 24, 2026