The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling

Zero Bubble Pipeline Parallelism

Inference code for LLaMA models in JAX

Provides a minimal implementation to extract FLAN datasets for further processing

Ongoing research training transformer models at scale

Generate SQL from Natural Language Sentences using OpenAI's GPT-3 Model

Implementation of Stochastic Beam Search using Fairseq

Dynamic Neural Semantic Parser

BiLSTM-CRF joint model for tasks like sequence labeling using char/word level embeddings in Tensorflow

Aho-Corasick的Java实现，针对Ascii优化，支持Unicode。

pyltp: the python extension for LTP

Tesseract Open Source OCR Engine (main repository)

中文版视频点这里：http://space.bilibili.com/18340402

C# wrapper around excellent wkhtmltopdf console utility.

Cheetah, the Python-powered templating engine

InterMine Github Issues Burn down chart

Fork of Pandoc for the implementation of a ScholarlyMarkdown parser

OSQA is a free, entry-level Q&A system from the makers of AnswerHub, the market-leading professional Q&A platform. Looking for Enterprise functionality? Checkout http://answerhub.com

(Deprecated) Lossless h.264 recoder/recompressor. For newest version see:

MarkdownJ

Adaptation of gxemul to support the CHERI MIPS unit test suite and certain CHERI features

A collection of css themes for Markdown