4 bits quantization of LLMs using GPTQ

Ongoing research training transformer language models at scale, including: BERT & GPT-2

[WMT 2022 champion system] Vega-MT model and inference scripts

Norm-Based Curriculum Learning for Neural Machine Translation (ACL 2020)

Pytorch Implementation of ALBERT(A Lite BERT for Self-supervised Learning of Language Representations)

An open-source tool for sequence learning in NLP built on TensorFlow.

fast python port of arc90's readability tool, updated to match latest readability.js!

Library for implementing RNNs with Theano

Wrapper for Keras with support to easy data loading and handling and the creation of staged networks.

pyltp: the python extension for LTP

A library for generalized sequence to sequence models