abditag2 / bertLinks
TensorFlow code and pre-trained models for BERT
☆24Updated 6 years ago
Alternatives and similar repositories for bert
Users that are interested in bert are comparing it to the libraries listed below
Sorting:
- Feel free to fine tune large BERT models with Multi-GPU and FP16 support.☆192Updated 5 years ago
- BERT distillation(基于BERT的蒸馏实验 )☆315Updated 5 years ago
- bert multiple gpu train pretrain☆29Updated 5 years ago
- multi-gpu pre-training in one machine for BERT without horovod (Data Parallelism)☆171Updated 6 months ago
- 对ACL2020 FastBERT论文的复现,论文地址//arxiv.org/pdf/2004.02178.pdf☆194Updated 3 years ago
- TensorFlow code and pre-trained models for BERT☆116Updated 5 years ago
- 基于tensorflow1.x的预训练模型调用,支持单机多卡、梯度累积,XLA加速,混合精度。可灵活训练、验证、预测。☆59Updated 4 years ago
- 个人基于谷歌开源的BERT编写的文本分类器(基于微调方式),可自由加载NLP领域知名的预训练语言模型BERT、Bert-wwm、Roberta、ALBert以及ERNIE1.0☆42Updated 5 years ago
- ☆220Updated 5 years ago
- TensorFlow code and pre-trained models for BERT and ERNIE☆147Updated 6 years ago
- ☆280Updated 4 years ago
- Collections of Chinese reading comprehension datasets☆220Updated 5 years ago
- 中文预训练XLNet模型: Pre-Trained Chinese XLNet_Large☆230Updated 6 years ago
- 将百度ernie的paddlepaddle模型转成tensorflow模型☆178Updated 5 years ago
- DIAC2019基于Adversarial Attack的问题等价性判别比赛☆82Updated 5 years ago
- A Sentence Cloze Dataset for Chinese Machine Reading Comprehension (CMRC 2019)☆127Updated 2 years ago
- Bert finetune for CMRC2018, CJRC, DRCD, CHID, C3☆184Updated 5 years ago
- 简单的向量白化改善句向量质量☆488Updated 4 years ago
- First place solution of WSDM CUP 2020, pairwise-bert, lightgbm☆89Updated 5 years ago
- baseline system of knowledge driven dialogue competition☆269Updated 6 years ago
- this is roberta wwm base distilled model which was distilled from roberta wwm by roberta wwm large☆65Updated 5 years ago
- DistilBERT for Chinese 海量中文预训练蒸馏bert模型☆94Updated 5 years ago
- tensorflow version of bert-of-theseus☆63Updated 4 years ago
- Deep contextualized word representations for Chinese☆151Updated 5 years ago
- This is a java version of Chinese tokenization descried in BERT.☆59Updated 2 years ago
- ☆168Updated 3 years ago
- The score code of FastBERT (ACL2020)☆608Updated 3 years ago
- cw2vec: Learning Chinese Word Embeddings with Stroke n-gram Information☆275Updated 2 years ago
- pytorch implementation for Patient Knowledge Distillation for BERT Model Compression☆203Updated 6 years ago
- chinese pretrain unilm☆28Updated 5 years ago