GlassyWing / transformer-kerasLinks
Using Keras + Tensor Flow to Implement Model Transformer in Paper "Attention Is All You Need". 使用 keras+tensorflow 实现论文"Attention Is All You Need"中的模型Transformer。
☆34Updated 7 years ago
Alternatives and similar repositories for transformer-keras
Users that are interested in transformer-keras are comparing it to the libraries listed below
Sorting:
- 这是使用pytoch 实现的长文本分类器☆46Updated 6 years ago
- DistilBERT for Chinese 海量中文预训练蒸馏bert模型☆95Updated 6 years ago
- Sequence labeling base on universal transformer (Transformer encoder) and CRF; 基于Universal Transformer + CRF 的中文分词和词性标注☆162Updated 6 years ago
- Dilate Gated Convolutional Neural Network For Machine Reading Comprehension☆39Updated 6 years ago
- Adversarial Training for NLP in Keras☆46Updated 5 years ago
- 中文 预训练 ELECTRA 模型: 基于对抗学习 pretrain Chinese Model☆141Updated 5 years ago
- tensorflow version of bert-of-theseus☆63Updated 5 years ago
- TestB榜第10的方案,bleu32.1☆63Updated 6 years ago
- 清博2019ccl幽默度识别第一名解决方案代码及说明☆41Updated 6 years ago
- 基于ELMo, tensorflow的中文命名实体标注 Chinese Named Entity Recognition Based on ELMo☆20Updated 6 years ago
- pytorch版bert权重转tf☆22Updated 5 years ago
- Adversarial Attack文本匹配比赛☆42Updated 6 years ago
- Final Project for EECS496-7☆62Updated 6 years ago
- 中文生成式预训练模型☆99Updated 5 years ago
- siamese dssm sentence_similarity sentece_similarity_rank tensorflow☆60Updated 7 years ago
- Bert finetune for CMRC2018, CJRC, DRCD, CHID, C3☆184Updated 5 years ago
- 将百度ernie的paddlepaddle模型转成tensorflow模型☆178Updated 6 years ago
- ☆44Updated 4 years ago
- keras sparse implement of margin-softmax☆100Updated 7 years ago
- 基于最小熵原理的NLP工具包☆139Updated 4 years ago
- Keras library for building (Universal) Transformers, facilitating BERT and GPT models☆11Updated 6 years ago
- language model in Chinese,基于Pytorch官方文档实现☆68Updated 7 years ago
- 中文版unilm预训练模型☆82Updated 4 years ago
- keras implement of dgcnn for reading comprehension☆164Updated 6 years ago
- 从头训练MASK BERT☆140Updated 3 years ago
- Knowledge Distillation from BERT☆54Updated 7 years ago
- 达观算法比赛ner任务,从重新训练bert,到finetune预测。☆75Updated 3 years ago
- datagrand 2019 information extraction competition rank9☆130Updated 6 years ago
- transformers implement (architecture, task example, serving and more)☆96Updated 3 years ago
- bert_chinese☆38Updated 3 years ago