Model Parallelism, Full Parameter, One Machine Multi GPUs

multi-gpu pre-training in one machine for BERT without horovod (Data Parallelism)

Data Parallelism, Full Parameter, One Machine Multi GPUs

Automatic Label Error Correction www.techrxiv.org/users/679328/articles/731085

Just for Fun

Just for Fun

Just for Fun

同义词表，反义词表，否定词表

三国群英传 武将不同天赋版

Content Enhanced BERT-based Text-to-SQL Generation https://arxiv.org/abs/1910.07179

code2text --> LLM --> text2code

code2image + code2text --> image2text --> text2code

Awesome Pdf/Ppt List

Revisiting Semantic Representation and Tree Search for Similar Question Retrieval https://arxiv.org/abs/1908.08326

TensorFlow等的Model的中文注释

Get AUC 0.794 at Movielens 20M dataset

Get AUC 0.809 at Criteo dataset by MLP

A Comprehensive Comparison of Pre-training Language Models https://arxiv.org/abs/2106.11483

金庸和古龙之间的文本风格转换

write my own neural network

Using Database Rule for Weak Supervised Text-to-SQL Generation https://arxiv.org/abs/1907.00620

Table2answer: Read the database and answer without SQL https://arxiv.org/abs/1902.04260

仙剑一MOD之武林盟主

开箱即用

named entity recognition combined with rule from entity dict

爬取百度百科数据，用于BERT预训练

大富翁4MOD 角色不同天赋版

PHP frontend for Apache Spark