jessevig/bertviz
▲ +6 ★ this week
BertViz: Visualize Attention in Transformer Models
BERT classification model for processing texts longer than 512 tokens. Text is first divided into smaller chunks and after feeding them to BERT, intermediate results are pooled. The implementation allows fine-tuning.
$ git clone https://github.com/mim-solutions/bert_for_longer_texts.git▲ +6 ★ this week
BertViz: Visualize Attention in Transformer Models
EasyNLP: A Comprehensive and Easy-to-use NLP Toolkit
This is the corresponding code for the book Transformers in Action
⛔ [NOT MAINTAINED] An End-To-End Closed Domain Question Answering System.
ExtremeBERT is a toolkit that accelerates the pretraining of customized language models on customized datasets, described in the paper “ExtremeBERT: A Toolkit for Accelerating Pretraining of Customized BERT”.
The official implementation of "EmoBERTa: Speaker-Aware Emotion Recognition in Conversation with RoBERTa"
Data from GitHub · snapshot Nov 16, 2026