47,133 repositories indexed
1–24 of 41 · Most stars
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
Offline, privacy-first grammar checker. Fast, open-source, Rust-powered
Topic Modelling for Humans
Pretrained models for TensorFlow.js
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
modest natural-language processing
Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
general natural language facilities for node
Open-source offline translation library written in Python
An NLP library for building bots, with entity extraction, sentiment analysis, automatic language identify, and so more
Easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code.
Bioinformatics'2020: BioBERT: a pre-trained biomedical language representation model for biomedical text mining
A full spaCy pipeline and models for scientific/biomedical documents.
Self-contained Machine Learning and Natural Language Processing library in Go
The most accurate natural language detection library for Go, suitable for short text and mixed-language text
Pretrained model hub for Keras 3.
Fast vectorization, topic modeling, distances and GloVe word embeddings in R.
🚀 Catalyst is a C# Natural Language Processing library built for speed. Inspired by spaCy's design, it brings pre-trained models, out-of-the box support for training word and document embeddings, and flexible entity recognition models.
A Modern C++ Data Sciences Toolkit
Translated斑海豹 (Spotted Seal) — Phocinae-Largha-150M-v1: a 144.3M bilingual decision model. Tiny model. Big decisions.