multi-gpu pre-training in one machine for BERT from scratch without horovod (Data Parallelism)
Support
Quality
Security
License
Reuse
Adversarial Training for Natural Language Understanding
Support
Quality
Security
License
Reuse
MPNet: Masked and Permuted Pre-training for Language Understanding https://arxiv.org/pdf/2004.09297.pdf
Support
Quality
Security
License
Reuse
XLNet for generating language.
Support
Quality
Security
License
Reuse
Distillation of KoBERT from SKTBrain (Lightweight KoBERT)
Support
Quality
Security
License
Reuse
LASER multilingual sentence embeddings as a pip package
Support
Quality
Security
License
Reuse
Source code for paper: Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data
Support
Quality
Security
License
Reuse
UDA(Unsupervised Data Augmentation) implemented by pytorch
Support
Quality
Security
License
Reuse
ac-library-rs is a rust port of AtCoder Library (ACL).
Support
Quality
Security
License
Reuse
pre-trained Language Models
Support
Quality
Security
License
Reuse
COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning
Support
Quality
Security
License
Reuse
Code and Data for ACL 2020 paper "Few-Shot NLG with Pre-Trained Language Model" https://arxiv.org/abs/1904.09521
Support
Quality
Security
License
Reuse
Summarization, translation, sentiment-analysis, text-generation and more at blazing speed using a T5 version implemented in ONNX.
Support
Quality
Security
License
Reuse
A painless way to pick future time.
Support
Quality
Security
License
Reuse
r
rethinking_performance_estimation_in_NASby MAC-AutoML
Python 
159
Version:Current
License: No License (No License)
Support
Quality
Security
License
Reuse
BERT for question answering starting with HotpotQA
Support
Quality
Security
License
Reuse
Implementation of XLNet that can load pretrained checkpoints
Support
Quality
Security
License
Reuse
transform multi-label classification as sentence pair task, with more training data and information
Support
Quality
Security
License
Reuse
WARNING: This package has been deprecated. Please use the SageMaker Training Toolkit for model training and the SageMaker Inference Toolkit for model serving.
Support
Quality
Security
License
Reuse
BERTRPC is a Ruby BERT-RPC client library.
Support
Quality
Security
License
Reuse
c
classifier_multi_label_textcnnby hellonlp
Python 
156
Version:Current
License: No License (No License)
multi-label,classifier,text classification,多标签文本分类,文本分类,BERT,ALBERT,multi-label-classification
Support
Quality
Security
License
Reuse
B
BERT_multimodal_transformerby WasifurRahman
Python 
155
Version:Current
License: No License (No License)
Support
Quality
Security
License
Reuse
Transformer language model (GPT-2) with sentencepiece tokenizer
Support
Quality
Security
License
Reuse
Pre-Trained Models for ToD-BERT
Support
Quality
Security
License
Reuse
D
Deploy-BERT-for-Sentiment-Analysis-with-FastAPIby curiousily
Python 
155
Version:Current
License: Permissive (MIT)
Deploy BERT for Sentiment Analysis as REST API using FastAPI, Transformers by Hugging Face and PyTorch
Support
Quality
Security
License
Reuse
Python wrapper for evaluating summarization quality by ROUGE package
Support
Quality
Security
License
Reuse
A list of pretrained Transformer models for the Russian language.
Support
Quality
Security
License
Reuse
Content Enhanced BERT-based Text-to-SQL Generation https://arxiv.org/abs/1910.07179
Support
Quality
Security
License
Reuse
QuickAI is a Python library that makes it extremely easy to experiment with state-of-the-art Machine Learning models.
Support
Quality
Security
License
Reuse
Label data using HuggingFace's transformers and automatically get a prediction service
Support
Quality
Security
License
Reuse
An unofficial implementation of Poly-encoder (Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring)
Support
Quality
Security
License
Reuse
对ACL2020 FastBERT论文的复现,论文地址:https://arxiv.org/pdf/2004.02178.pdf
Support
Quality
Security
License
Reuse
Scalable Topic Modeling using Variational Inference in MapReduce
Support
Quality
Security
License
Reuse
Neural models for Text Classification in Tensorflow, such as cnn, dpcnn, fasttext, bert ...
Support
Quality
Security
License
Reuse
pre-training and fine-tuning framework for text generation
Support
Quality
Security
License
Reuse
All For NLP, especially Chinese.
Support
Quality
Security
License
Reuse
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
Support
Quality
Security
License
Reuse
a Fast, Flexible, Extensible and Easy-to-use NLP Large-scale Pretraining and Multi-task Learning Framework.
Support
Quality
Security
License
Reuse
Code for the article "Semantic-Unit-Based Dilated Convolution for Multi-Label Text Classification" (EMNLP 2018)
Support
Quality
Security
License
Reuse
Scripts to train a bidirectional LSTM with knowledge distillation from BERT
Support
Quality
Security
License
Reuse
NLP research:基于tensorflow的nlp深度学习项目,支持文本分类/句子匹配/序列标注/文本生成 四大任务
Support
Quality
Security
License
Reuse
语义理解/口语理解,项目包含有词法分析:中文分词、词性标注、命名实体识别;口语理解:领域分类、槽填充、意图识别。
Support
Quality
Security
License
Reuse
[ACM MM 2018] Attribute-Aware Attention Model for Fine-grained Representation Learning
Support
Quality
Security
License
Reuse
TextAugment: Text Augmentation Library
Support
Quality
Security
License
Reuse
Framework for fine-tuning pretrained transformers for Named-Entity Recognition (NER) tasks
Support
Quality
Security
License
Reuse
E
Elmo-Tutorialby PrashantRanjan09
Jupyter Notebook 
146
Version:Current
License: No License (No License)
A short tutorial on Elmo training (Pre trained, Training on new data, Incremental training)
Support
Quality
Security
License
Reuse
Code for the NeurIPS'17 paper "DropoutNet: Addressing Cold Start in Recommender Systems"
Support
Quality
Security
License
Reuse
Soft-Masked Bert 复现论文:https://arxiv.org/pdf/2005.07421.pdf
Support
Quality
Security
License
Reuse
Assessing syntactic abilities of BERT
Support
Quality
Security
License
Reuse
天池大赛疫情文本挑战赛线上第三名方案分享
Support
Quality
Security
License
Reuse
B
BERT-GPUby guotong1988
multi-gpu pre-training in one machine for BERT from scratch without horovod (Data Parallelism)
Python
164
Updated: 2 y ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
F
FreeLBby zhuchen03
Adversarial Training for Natural Language Understanding
Python
164
Updated: 4 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
M
MPNetby microsoft
MPNet: Masked and Permuted Pre-training for Language Understanding https://arxiv.org/pdf/2004.09297.pdf
Python
164
Updated: 4 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
X
XLnet-genby rusiaaman
XLNet for generating language.
Python
164
Updated: 4 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
D
DistilKoBERTby monologg
Distillation of KoBERT from SKTBrain (Lightweight KoBERT)
Python
163
Updated: 2 y ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
l
laserembeddingsby yannvgn
LASER multilingual sentence embeddings as a pip package
Python
163
Updated: 3 y ago
License: Permissive (BSD-3-Clause)
Support
Quality
Security
License
Reuse
f
fairseq-gecby zhawe01
Source code for paper: Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data
Python
162
Updated: 5 y ago
License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
U
UDA_pytorchby SanghunYun
UDA(Unsupervised Data Augmentation) implemented by pytorch
Python
162
Updated: 4 y ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
a
ac-library-rsby rust-lang-ja
ac-library-rs is a rust port of AtCoder Library (ACL).
Rust
162
Updated: 2 y ago
License: Permissive (CC0-1.0)
Support
Quality
Security
License
Reuse
l
language-modelsby piegu
pre-trained Language Models
Jupyter Notebook
162
Updated: 2 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
c
coot-videotextby gingsi
COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning
Python
161
Updated: 4 y ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
F
Few-Shot-NLGby czyssrs
Code and Data for ACL 2020 paper "Few-Shot NLG with Pre-Trained Language Model" https://arxiv.org/abs/1904.09521
Python
160
Updated: 4 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
o
onnxt5by abelriboulot
Summarization, translation, sentiment-analysis, text-generation and more at blazing speed using a T5 version implemented in ONNX.
Python
159
Updated: 4 y ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
D
DateTimeSeerby p-v
A painless way to pick future time.
Java
159
Updated: 4 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
r
rethinking_performance_estimation_in_NASby MAC-AutoML
Python
159
Updated: 3 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
b
bert-qaby chiayewken
BERT for question answering starting with HotpotQA
Python
158
Updated: 4 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
k
keras-xlnetby CyberZHG
Implementation of XLNet that can load pretrained checkpoints
Python
157
Updated: 4 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
m
multi-label_classificationby brightmart
transform multi-label classification as sentence pair task, with more training data and information
Python
157
Updated: 4 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
s
sagemaker-containersby aws
WARNING: This package has been deprecated. Please use the SageMaker Training Toolkit for model training and the SageMaker Inference Toolkit for model serving.
Python
157
Updated: 4 y ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
b
bertrpcby mojombo
BERTRPC is a Ruby BERT-RPC client library.
Ruby
157
Updated: 4 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
c
classifier_multi_label_textcnnby hellonlp
multi-label,classifier,text classification,多标签文本分类,文本分类,BERT,ALBERT,multi-label-classification
Python
156
Updated: 4 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
B
BERT_multimodal_transformerby WasifurRahman
Python
155
Updated: 2 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
t
transformer-lmby lopuhin
Transformer language model (GPT-2) with sentencepiece tokenizer
Python
155
Updated: 4 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
T
ToD-BERTby jasonwu0731
Pre-Trained Models for ToD-BERT
Python
155
Updated: 4 y ago
License: Permissive (BSD-2-Clause)
Support
Quality
Security
License
Reuse
D
Deploy-BERT-for-Sentiment-Analysis-with-FastAPIby curiousily
Deploy BERT for Sentiment Analysis as REST API using FastAPI, Transformers by Hugging Face and PyTorch
Python
155
Updated: 2 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
p
pythonrougeby tagucci
Python wrapper for evaluating summarization quality by ROUGE package
Perl
155
Updated: 4 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
t
transformers-ruby vlarine
A list of pretrained Transformer models for the Russian language.
Jupyter Notebook
155
Updated: 4 y ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
N
NL2SQL-RULEby guotong1988
Content Enhanced BERT-based Text-to-SQL Generation https://arxiv.org/abs/1910.07179
Python
154
Updated: 2 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
q
quickaiby geekjr
QuickAI is a Python library that makes it extremely easy to experiment with state-of-the-art Machine Learning models.
Python
154
Updated: 2 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
l
label-studio-transformersby heartexlabs
Label data using HuggingFace's transformers and automatically get a prediction service
Python
153
Updated: 2 y ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
P
PolyEncoderby sfzhou5678
An unofficial implementation of Poly-encoder (Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring)
Python
153
Updated: 4 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
F
FastBERTby BitVoyage
对ACL2020 FastBERT论文的复现,论文地址:https://arxiv.org/pdf/2004.02178.pdf
Python
153
Updated: 4 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
M
Mr.LDAby lintool
Scalable Topic Modeling using Variational Inference in MapReduce
Java
151
Updated: 4 y ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
t
text-classification-demosby liyibo
Neural models for Text Classification in Tensorflow, such as cnn, dpcnn, fasttext, bert ...
Python
151
Updated: 4 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
G
Guyuby lipiji
pre-training and fine-tuning framework for text generation
Python
150
Updated: 4 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
A
All4NLPby hscspring
All For NLP, especially Chinese.
Jupyter Notebook
150
Updated: 4 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
t
transformer-word-segmenterby GlassyWing
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
Python
149
Updated: 2 y ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
P
PALMby PaddlePaddle
a Fast, Flexible, Extensible and Easy-to-use NLP Large-scale Pretraining and Multi-task Learning Framework.
Python
148
Updated: 2 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
S
SU4MLCby lancopku
Code for the article "Semantic-Unit-Based Dilated Convolution for Multi-Label Text Classification" (EMNLP 2018)
Python
148
Updated: 4 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
d
distil-bilstmby tacchinotacchi
Scripts to train a bidirectional LSTM with knowledge distillation from BERT
Python
147
Updated: 4 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
n
nlp_researchby zhufz
NLP research:基于tensorflow的nlp深度学习项目,支持文本分类/句子匹配/序列标注/文本生成 四大任务
Python
146
Updated: 4 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
S
Semanticby ownthink
语义理解/口语理解,项目包含有词法分析:中文分词、词性标注、命名实体识别;口语理解:领域分类、槽填充、意图识别。
Python
146
Updated: 4 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
a
attribute-aware-attentionby iamhankai
[ACM MM 2018] Attribute-Aware Attention Model for Fine-grained Representation Learning
Python
146
Updated: 4 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
t
textaugmentby dsfsi
TextAugment: Text Augmentation Library
Python
146
Updated: 4 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
N
NERDAby ebanalyse
Framework for fine-tuning pretrained transformers for Named-Entity Recognition (NER) tasks
Python
146
Updated: 2 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
E
Elmo-Tutorialby PrashantRanjan09
A short tutorial on Elmo training (Pre trained, Training on new data, Incremental training)
Jupyter Notebook
146
Updated: 4 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
D
DropoutNetby layer6ai-labs
Code for the NeurIPS'17 paper "DropoutNet: Addressing Cold Start in Recommender Systems"
Python
145
Updated: 2 y ago
License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
S
SoftMaskedBertby hiyoung123
Soft-Masked Bert 复现论文:https://arxiv.org/pdf/2005.07421.pdf
Python
145
Updated: 4 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
b
bert-syntaxby yoavg
Assessing syntactic abilities of BERT
Python
145
Updated: 4 y ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
e
epidemicTextMatchby huanghuidmml
天池大赛疫情文本挑战赛线上第三名方案分享
Python
145
Updated: 4 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse