jiezhanggt Goto Github PK

adaptive-knn-mt

albert_zh

A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS, 海量中文预训练ALBERT模型

autogluon

AutoGluon: AutoML Toolkit for Deep Learning

autogpt

An experimental open-source attempt to make GPT-4 fully autonomous.

awesome-llm-mt

belle

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

bert

TensorFlow code and pre-trained models for BERT

bert-as-service

Mapping a variable-length sentence to a fixed-length vector using BERT model

bert-for-task

bert-of-theseus

⛵️The official PyTorch implementation for "BERT-of-Theseus: Compressing BERT by Progressive Module Replacing".

bleualign

Machine-Translation-based sentence alignment tool for parallel text

bmcook

Model Compression for Big Models

cdalign

Code for AAAI 2021 paper "Lexically Constrained Neural Machine Translation with Explicit Alignment Guidance"

chinese-llama-alpaca

中文LLaMA&Alpaca大语言模型+本地CPU/GPU部署 (Chinese LLaMA & Alpaca LLMs)

chinese-names-corpus

中文人名语料库。人名生成器。中文姓名,姓氏,名字,称呼,日本人名,翻译人名,英文人名。可用于中文分词、人名实体识别。

chinese-xinhua

:orange_book: 中华新华字典数据库。包括歇后语，成语，词语，汉字。

clue

中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard

cnn-text-classification-pytorch

CNNs for Sentence Classification in PyTorch

coder2gwy

互联网首份程序员考公指南，由3位已经进入体制内的前大厂程序员联合献上。

coding-interview-university

A complete computer science study plan to become a software engineer.

colossalai

Making big AI models cheaper, easier, and scalable

comet

A Neural Framework for MT Evaluation

compare-mt

A tool for holistic analysis of language generations systems

coverage-contrastive-conditioning

Data and code accompanying the paper "As Little as Possible, as Much as Necessary: Detecting Over- and Undertranslations with Contrastive Conditioning" (ACL 2022)

cpm-bee

百亿参数的中英文双语基座大模型

cpm-live

Live Training for Open-source Big Models

deepspeed

DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

douyin-hot-hub

记录抖音热榜、明星榜、直播榜、音乐榜和品牌榜，每小时更新，按天归档。

eda_nlp_for_chinese

An implement of the paper of EDA for Chinese corpus.中文语料的EDA数据增强工具。NLP数据增强。论文阅读笔记。

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.