Language Models
codertimo/BERT-pytorch
Google AI 2018 BERT pytorch implementation
π§ Natural Language Processing
PythonApache-2.0updated Sep 15, 2023
Transformer with Untied Positional Encoding (TUPE). Code of paper "Rethinking Positional Encoding in Language Pre-training". Improve existing models like BERT.
$ git clone https://github.com/guolinke/TUPE.gitGoogle AI 2018 BERT pytorch implementation
[ACL 2022] LinkBERT: A Knowledgeable Language Model π Pretrained with Document Links
[NeurIPS 2022] DRAGON π²: Deep Bidirectional Language-Knowledge Graph Pretraining
ExtremeBERT is a toolkit that accelerates the pretraining of customized language models on customized datasets, described in the paper βExtremeBERT: A Toolkit for Accelerating Pretraining of Customized BERTβ.
A framework for few-shot evaluation of language models.
Data from GitHub Β· snapshot Sep 24, 2026