← Explore by area/BERT and Transformer-based NLP

BERT and Transformer-based NLP

29 repos

Libraries, implementations, and applications of BERT and transformer models for natural language processing tasks across multiple languages. The cluster includes core model implementations (ModernBERT, KoBERT, KcBERT), language-specific fine-tuning efforts like Turkish and Korean sentiment analysis, and foundational tools for working with these architectures. Most repos are Python-based research implementations and Jupyter notebooks exploring model variations, training approaches, and downstream NLP applications.

Python · 15

Jupyter Notebook · 12

Rust · 1

nlp ·26,508

bert ·26,508

transformers ·21,473

language-model ·12,523

natural-language-processing ·11,883

natural-language-understanding ·11,018

gpt ·11,018

machine-learning ·7,998

ldavis ·7,831

sentence-embeddings ·7,831

Related clusters

LLM and NLP Model Adaptation12 Natural Language Processing & Text Analysis40 Cluster 45424922 Cluster 44140615 Text Embedding Models & Inference34 Cluster 44034818

hppRC/defsent

DefSent: Sentence Embeddings using Definition Sentences

Python

6 commits

AnswerDotAI/ModernBERT

Bringing BERT into modernity via both architecture changes and scaling

Python

1,720

231 commits

izzetemredemir/turkish-sentiment-analysis-with-bert

Simple NLP project. Turkish sentiment analysis with bert.

Python

4 commits

asahi417/relbert

The official implementation of "Distilling Relation Embeddings from Pre-trained Language Models,…

Python

688 commits

SKTBrain/KoBERT

Korean BERT pre-trained cased (KoBERT)

Python

1,420

90 commits

Beomi/KcBERT

🤗 Pretrained BERT model & WordPiece tokenizer trained on Korean Comments 한국어 댓글로 프리트레이닝한 BERT 모델과…

497

34 commits

mbahadirk/Offensive-Text-Classification

Turkish Toxic Comment Classification

Jupyter Notebook

60 commits

sagorbrur/bangla-bert

Bangla-Bert is a pretrained bert model for Bengali language

Jupyter Notebook

54 commits

huggingface/tokenizers

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

Rust

11,018

2,000 commits

MuhammetCanGumussu/Bert-Implementation-From-Scratch

No description

Jupyter Notebook

69 commits

a-v-ershov/russian_sentiment_analysis

Sequence classification model for sentiment analysis of Russian conversational text

Jupyter Notebook

7 commits

matheuscamposmt/food-hazard-bert

A Natural Language Processing (NLP) project for SemEval 2025 Task 9, using DistilBERT with a custom…

Jupyter Notebook

20 commits

mlwithme/BertWithPretrained

An implementation of the BERT model and its related downstream tasks based on the PyTorch…

Python

603

240 commits

naver/splade

SPLADE: sparse neural search (SIGIR21, SIGIR22)

Python

1,011

113 commits

Hugging-Face-Supporter/tftokenizers

Use Huggingface Transformer and Tokenizers as Tensorflow Reusable SavedModels

Python

7 commits

l3cube-pune/MarathiNLP

Marathi NLP - is a repository dedicated to development of tools and resources for Marathi language.

Jupyter Notebook

163

160 commits

Turkish-Word-Embeddings/Word-Embeddings-Repository-for-Turkish

Code for "A Comprehensive Analysis of Static Word Embeddings for Turkish". Expert Systems with…

Jupyter Notebook

114 commits

KRLabsOrg/LettuceDetect

Span-level grounding verification for RAG, code, and tool-grounded AI outputs.

Python

606

218 commits

voorhs/dialogue-augmentation

Research project on Contrastive Learning with Augmentations for Training Dialogue Embeddings

Jupyter Notebook

147 commits

MaartenGr/BERTopic

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

Python

7,831

188 commits

wisdomify/wisdomify

A BERT-based reverse dictionary of Korean proverbs

Python

170 commits

gerzin/irony-and-sarcasm-detector-italian

NLP project that analyses Italian tweets and finds out if they are ironic or not, and if they're…

Jupyter Notebook

132 commits

legacyai/tf-transformers

State of the art faster Transformer with Tensorflow 2.0 ( NLP, Computer Vision, Audio ).

Jupyter Notebook

383 commits

umarbutler/emubert-creator

The training code behind EmuBert, the largest open-source masked language model for Australian law.

Python

8 commits

isaacus-dev/emubert-creator

The training code behind EmuBert, the largest open-source masked language model for Australian law.

Python

8 commits

metehan777/google-rerank-tool

A Python cli-command tool for creating reports for any Google query.

Python

9 commits

ukairia777/tensorflow-nlp-tutorial

tensorflow를 사용하여 텍스트 전처리부터, Topic Models, BERT, GPT, LLM과 같은 최신 모델의 다운스트림 태스크들을 정리한 Deep Learning…

Jupyter Notebook

581

265 commits

yachiashen/DeFake-ZH

Chinese Fake News Detection based on MacBERT

Python

38 commits

indobenchmark/indonlu

The first-ever vast natural language processing benchmark for Indonesian Language. We provide…

Jupyter Notebook

655

104 commits