xv44586's repositories
ccf_2020_qa_match
ccf 2020 qa match competition top1
Chinese-instruction-datasets
中文 Instruction tuning datasets
toolkit4nlp
transformers implement (architecture, task example, serving and more)
Knowledge-Distillation-NLP
some demos of Knowledge Distillation in NLP
tianchi_multitask
天池中文预训练语言模型比赛
fire_datasets
fire datasets
faster-decoder
make decoder inference faster
xv44586.github.io
https://xv44586.github.io/
bert4keras
keras implement of transformers for humans
dict_build
自动构建中文词库:http://www.matrix67.com/blog/archives/5044
chinese-poetry
最全中华古诗词数据库, 唐宋两朝近一万四千古诗人, 接近5.5万首唐诗加26万宋诗. 两宋时期1564位词人,21050首词。
GLM
GLM (General Language Model)
go-common
哔哩哔哩 bilibili 网站后台工程 源码
gpt-neox
An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
hexo-theme-skapp
The hexo flat design theme(扁平化简约主题)
pdfplumber
Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.