Taoooo

ian-xiaohei-illustrations. 中文小黑怪诞正文配图生成 Skill | 16:9 白底手绘 | 少量红橙蓝批注 | Codex Skill

learn-claude-code. Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

claude-plugins-official. Official, Anthropic-managed directory of high quality Claude Code Plugins.

ui-ux-pro-max-skill. An AI SKILL that provide design intelligence for building professional UI/UX multiple platforms

andrej-karpathy-skills. A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Understand-Anything. Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

agent-skills-with-anthropic. 本项目围绕吴恩达老师在DeepLearning.AI出品的agent-skills-with-anthropic系列课程，为学习者打造中文翻译与知识整理教程。项目提供课程内容翻译、知识点梳理和示例代码解读等内容，欢迎大家Star!

camel. 🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

ppt-master. AI generates a real, editable PowerPoint from any document — native shapes & animations, editable charts & tables you can change the data on, speaker notes voiced as audio narration, and the option to follow your own .pptx template, not slide images · by Hugo He

hermes-agent. The agent that grows with you

vibe-coding-cn. Vibe Coding 从入门到精通教程｜AI 结对编程工作流｜Prompt、Skill、Workflow、上下文管理、codex实战指南

harness-engineering. Harness Engineering 学习指南 — 从概念理解到独立实践的深度学习档案

ECC. The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Awesome-Redteam. 一个攻防知识库。A knowledge base for red teaming and offensive security.

zhangxuefeng-skill. 张雪峰.skill — 张雪峰的认知操作系统。高考志愿/考研/职业规划的实战思维框架。由女娲.skill生成。

planning-with-files. Persistent file-based planning for AI coding agents and long-running agentic tasks. Crash-proof markdown plans that survive context loss and /clear, plus a deterministic completion gate and multi-agent shared state on disk. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard.

banana-slides. 一个基于nano banana pro🍌的原生AI PPT生成应用，迈向＂Vibe PPT＂; 支持上传任意模板图片，上传任意素材&智能解析，一句话/大纲/页面描述自动生成PPT，口头修改指定区域、一键导出可编辑ppt - An AI-native slides generator based on nano banana pro🍌

BettaFish. 微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

iMontage. iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation

Awesome-Nano-Banana-images. A curated collection of fun and creative examples generated with Nano Banana & Nano Banana Pro🍌, Gemini-2.5-flash-image based model. We also release Nano-consistent-150K openly to support the community's development of image generation and unified models(click to website to see our blog)

git-lfs. Git extension for versioning large files

xiaomi-miloco. Xiaomi Miloco

Video-RAG-master. ✨✨[NeurIPS 2025] This is the official implementation of our paper "Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension"

VideoRAG. [KDD'2026] "VideoRAG: Chat with Your Videos"

chinese_province_city_area_mapper. 一个用于提取简体中文字符串中省，市和区并能够进行映射，检验和简单绘图的python模块

MCP-Chinese-Getting-Started-Guide. Model Context Protocol(MCP) 编程极速入门

True-Story-of-Pangu. 诺亚盘古大模型研发背后的真正的心酸与黑暗的故事。

ChinaTextbook. 所有小初高、大学PDF教材。

EasyR1. EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

Visual-RFT. Official repository of 'Visual-RFT: Visual Reinforcement Fine-Tuning' & 'Visual-ARFT: Visual Agentic Reinforcement Fine-Tuning'’

ScreenAI. Implementation of the ScreenAI model from the paper: "A Vision-Language Model for UI and Infographics Understanding"

VLM-R1. Solve Visual Understanding with Reinforced VLMs

R1-Onevision. R1-onevision, a visual language model capable of deep CoT reasoning.

open-infra-index. Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

finetune-Qwen2-VL. Python

Qwen-VL-Series-Finetune. An open-source implementaion for fine-tuning Qwen-VL series by Alibaba Cloud.

Qwen3-VL. Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

UI-TARS. Pioneering Automated GUI Interaction with Native Agents

DeepSeek-V3. Python

minillm. MiniLLM is a minimal system for running modern LLMs on consumer-grade GPUs

LLM-Distillery. A pipeline for LLM knowledge distillation

Awesome-Knowledge-Distillation-of-LLMs. This repository collects papers for "A Survey on Knowledge Distillation of Large Language Models". We break down KD into Knowledge Elicitation and Distillation Algorithms, and explore the Skill & Vertical Distillation of LLMs.

distillm. Official PyTorch implementation of DistiLLM: Towards Streamlined Distillation for Large Language Models (ICML 2024)

Awesome-LLM-Learning. Learning Large Language Model (LLM）(大语言模型学习)

ShowUI. [CVPR 2025] Open-source, End-to-end, Vision-Language-Action model for GUI Agent & Computer Use.

ScreenAgent. ScreenAgent: A Computer Control Agent Driven by Visual Language Large Model (IJCAI-24)

Medusa. Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

Awesome-Multimodal-Large-Language-Models. :sparkles::sparkles:Latest Advances on Multimodal Large Language Models

Monkey. Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models (CVPR 2024 Highlight)

adan_application. 一些大语言模型和多模态模型的生态,主要包括跨模态搜索、投机解码、QAT量化、多模态量化、ChatBot、OCR

vllm. A high-throughput and memory-efficient inference and serving engine for LLMs

Awesome-Multimodal-Large-Language-Models. Reading notes about Multimodal Large Language Models, Large Language Models, and Diffusion Models

CAL. [NeurIPS'24] Official PyTorch Implementation of Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment

AiPPT. AI 智能生成 PPT，通过主题/文件/网址等方式生成PPT，支持原生图表、动画、3D特效等复杂PPT的解析和渲染，支持用户自定义模板，支持智能添加动画，可在线体验。AI generates PowerPoint Presentation, Supports parsing and rendering of complex PPT features such as native charts, animations, and 3D effects.

screen_qa. ScreenQA dataset was introduced in the "ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots" paper. It contains ~86K question-answer pairs collected by human annotators for ~35K screenshots from Rico. It should be used to train and evaluate models capable of screen content understanding via question answering.

ms-swift. Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).

FastGPT. FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.

InternVL. [CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

CogVLM2. GPT4V-level open-source multi-modal model based on Llama3-8B

MultimodalOCR. On the Hidden Mystery of OCR in Large Multimodal Models (OCRBench)

ml-ferret. Python

GLM-4. GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

MiniCPM-V. A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone

MaxKB. 🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

ragflow. RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

direct-preference-optimization. Reference implementation for DPO (Direct Preference Optimization)

Awesome-Hupu. 虎扑评分导航

bagel. A bagel, with everything.

mergekit. Tools for merging pretrained large language models.

Firefly-LLaMA2-Chinese. Firefly中文LLaMA-2大模型，支持增量预训练Baichuan2、Llama2、Llama、Falcon、Qwen、Baichuan、InternLM、Bloom等大模型

XAgent. An Autonomous LLM Agent for Complex Task Solving

FlagEmbedding. Retrieval and Retrieval-augmented LLMs

ChineseSemanticKB. ChineseSemanticKB,chinese semantic knowledge base, 面向中文处理的12类、百万规模的语义常用词典，包括34万抽象语义库、34万反义语义库、43万同义语义库等，可支持句子扩展、转写、事件抽象与泛化等多种应用场景。

Baichuan2. A series of large language models developed by Baichuan Intelligent Technology

LexiLaw. LexiLaw - 中文法律大模型

awesome-chinese-legal-resources. 📝 An Awesome Collection of Chinese Legal Dataset and Relevant Resources. 致力于收集全面的中文法律数据源

llm-action. 本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

CoDeF. [CVPR'24 Highlight] Official PyTorch implementation of CoDeF: Content Deformation Fields for Temporally Consistent Video Processing

Awesome-Chinese-LLM. 整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

AlignLLMHumanSurvey. Aligning Large Language Models with Human: A Survey

BibiGPT-v1. BibiGPT v1 · one-Click AI Summary for Audio/Video & Chat with Learning Content: Bilibili | YouTube | Tweet丨TikTok丨Dropbox丨Google Drive丨Local files | Websites丨Podcasts | Meetings | Lectures, etc. 音视频内容 AI 一键总结 & 对话：哔哩哔哩丨YouTube丨推特丨小红书丨抖音丨快手丨百度网盘丨阿里云盘丨网页丨播客丨会议丨本地文件等 (原 BiliGPT 省流神器 & AI课代表)

Chinese-CLIP. Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

Baichuan-13B. A 13B large language model developed by Baichuan Intelligent Technology

Poetry. 非常全的古诗词数据，收录了从先秦到现代的共计85万余首古诗词。

MuCGEC. MuCGEC中文纠错数据集及文本纠错SOTA模型开源；Code & Data for our NAACL 2022 Paper "MuCGEC: a Multi-Reference Multi-Source Evaluation Dataset for Chinese Grammatical Error Correction"

langchain. The agent engineering platform.

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

chinese-llm-benchmark. 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。

DragGAN. Official Code for DragGAN (SIGGRAPH 2023)

NextChat. ✨ Light and Fast AI Assistant. Support: Web | iOS | MacOS | Android | Linux | Windows

DecryptPrompt. 总结Prompt&LLM论文，开源数据&模型，AIGC应用

Baichuan-7B. A large-scale 7B pretraining language model developed by BaiChuan-Inc.

stable-diffusion-webui. Stable Diffusion web UI

AnimeGANv2. [Open Source]. The improved version of AnimeGAN. Landscape photos/videos to anime

OpenBuddy. Open Multilingual Chatbot for Everyone

YuLan-Chat. YuLan: An Open-Source Large Language Model

uniem. unified embedding model

ToolBench. [ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.

gptlink. 10分钟搭建可免费商用的AI对话环境，搭建简单，包含用户，订单，任务，付费等功能

Awesome-Multimodal-LLM. Research Trends in LLM-guided Multimodal Learning.

prm800k. 800,000 step-level correctness labels on LLM solutions to MATH problems

goat. a Fine-tuned LLaMA that is Good at Arithmetic Tasks

CPM-Bee. 百亿参数的中英文双语基座大模型

jieba_fast. Use C Api and Swig to Speed up jieba 高效的中文分词库

NBCE. Naive Bayes-based Context Extension

qlora. QLoRA: Efficient Finetuning of Quantized LLMs

safe-rlhf. Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

GPT-Prompts. Useful GPT Prompts

sgpt. SGPT: GPT Sentence Embeddings for Semantic Search

deep_training. deep learning

Firefly. Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

Chinese-LangChain. 中文langchain项目|小必应，Q.Talk，强聊，QiangTalk

LLMZoo. ⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡

SuperCLUE. SuperCLUE: 中文通用大模型综合性基准 | A Benchmark for Foundation Models in Chinese

ChatYuan. ChatYuan: Large Language Model for Dialogue in Chinese and English

LLMPruner. Python

LangChain-Chinese-Getting-Started-Guide. LangChain 的中文入门教程

gpt4free. The official gpt4free repository | various collection of powerful language models | opus 4.6 gpt 5.3 kimi 2.5 deepseek v3.2 gemini 3

Prompt-Engineering-Guide-Chinese. Prompt工程师指南，源自英文版，但增加了AIGC的prompt部分，为了降低同学们的学习门槛，翻译更新

Langchain-Chatchat. Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain

so-vits-svc-fork. so-vits-svc fork with realtime support, improved interface and more features.

LLaMA-Cult-and-More. Large Language Models for All, 🦙 Cult and More, Stay in touch !

textgen. TextGen: Implementation of Text Generation models, include LLaMA, BLOOM, GPT2, BART, T5, SongNet and so on. 文本生成模型，实现了包括LLaMA，ChatGLM，BLOOM，GPT2，Seq2Seq，BART，T5，UDA等模型的训练和预测，开箱即用。

LLaVA. [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

MiniGPT-4. Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

MOSS. An open-source tool-augmented conversational language model from Fudan University

Bloom-Lora. Finetune Bloom big language model with Lora method

DeepSpeedExamples. Example models using DeepSpeed

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

AgentGPT. 🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.

AutoGPT. AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

Chinese-Vicuna. Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca

LMFlow. An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

FastChat. An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

LoRA-ViT. Low rank adaptation for Vision Transformer

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

zero_nlp. 中文nlp解决方案(大模型、数据、模型、训练、推理)

alpaca-chinese-dataset. alpaca中文指令微调数据集

chat-dataset-baseline. 人工精调的中文对话数据集和一段chatglm的微调代码

pytorch-image-models. The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

Alpaca-CoT. We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts to initiate any meaningful PR on this repo and integrate as many LLM related technologies as possible. 我们打造了方便研究人员上手和使用大模型等微调平台，我们欢迎开源爱好者发起任何有意义的pr！

peft. 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

ChatGLM-Tuning. 基于ChatGLM-6B + LoRA的Fintune方案

Linly. Chinese-LLaMA 1&2、Chinese-Falcon 基础模型；ChatFlow中文对话模型；中文OpenLLaMA模型；NLP预训练/指令微调数据集

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

alpaca-lora. Instruct-tune LLaMA on consumer hardware

chatglm_finetuning. chatglm 6b finetuning and alpaca finetuning

gradio. Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

stanford_alpaca. Code and documentation to train Stanford's Alpaca models, and generate the data.

ChatPaper. Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复

ChatGLM-6B. ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

OpenChatKit. Python

modelscope. ModelScope: bring the notion of Model-as-a-Service to life.

llama. Inference code for Llama models

NLPer-Interview. 该仓库主要记录 NLP 算法工程师相关的面试题

ColossalAI. Making large AI models cheaper, faster and more accessible

ChineseAiDungeonChatGPT. 中文版的ai地牢，直接使用的openai的ChatGPT api作为讲故事的模型。

CLIP-Chinese. 中文CLIP预训练模型

PromptCLUE. PromptCLUE, 全中文任务支持零样本学习模型

pCLUE. pCLUE: 1000000+多任务提示学习数据集

NLPer-Arsenal. 收录NLP竞赛策略实现、各任务baseline、相关竞赛经验贴（当前赛事、往期赛事、训练赛）、NLP会议时间、常用自媒体、GPU推荐等，持续更新中

stable-diffusion. A latent text-to-image diffusion model

pyunit-time. 一个简单易用的 Python 模块，用于通过字符串来操作日期/时间。正则时间提取，字符串时间解析，字符串时间提取。中文时间提取，一句话里面提取时间

nlp_chinese_corpus. 大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP

NLPDataSet. 记录本人整理的一些数据集

PaddleNLP. Easy-to-use and powerful LLM and SLM library with awesome model zoo.

HanLP. 中文分词 词性标注 命名实体识别 依存句法分析 成分句法分析 语义依存分析 语义角色标注 指代消解 风格转换 语义相似度 新词发现 关键词短语提取 自动摘要 文本分类聚类 拼音简繁转换 自然语言处理

bertviz. BertViz: Visualize Attention in Transformer Models

Text2Event. Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction

CLUEDatasetSearch. 搜索所有中文NLP数据集，附常用英文NLP数据集

Event-Extraction. 近年来事件抽取方法总结，包括中文事件抽取、开放域事件抽取、事件数据生成、跨语言事件抽取、小样本事件抽取、零样本事件抽取等类型，DMCNN、FramNet、DLRNN、DBRNN、GCN、DAG-GRU、JMEE、PLMEE等方法

HowToCook. Programmer's guide about how to cook at home.

Transfer-Learning-Library. Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization

pyecharts. 🎨 Python Echarts Plotting Library

neural-ranking-kd. Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation

cn2an. 📦 快速转化「中文数字」和「阿拉伯数字」～ (最新特性：分数，日期、温度等转化）

python-string-similarity. A library implementing different string similarity and distance measures using Python.

NLP-Interview-Notes. 该仓库主要记录 NLP 算法工程师相关的面试题

Chinese-NLP-Corpus. Collections of Chinese NLP corpus

nlpcda. 一键中文数据增强包 ； NLP数据增强、bert数据增强、EDA：pip install nlpcda

zero-shot-image-to-text. Implementation of Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic

Fengshenbang-LM. Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

Time_NLP. Time-NLP的python3版本 中文时间表达词转换

PromptPapers. Must-read papers on prompt-based tuning for pre-trained language models.

awesome-pretrained-chinese-nlp-models. Awesome Pretrained Chinese NLP Models，高质量中文预训练模型&大模型&多模态模型&大语言模型集合

paper-reading. 深度学习经典、新论文逐段精读

Mengzi. Mengzi Pretrained Models

OptiPrompt. [NAACL 2021] Factual Probing Is [MASK]: Learning vs. Learning to Recall https://arxiv.org/abs/2104.05240

BMInf. Efficient Inference for Big Models

pytorch-optimizer. torch-optimizer -- collection of optimizers for Pytorch

SinglepassTextCluster. SinglepassTextCluster, an TextCluster tools based on Singlepass cluster algorithm that use tfidf vector and doc2vec，which can be used for individual real-time corpus cluster task。基于single-pass算法思想的自动文本聚类小组件，内置tfidf和doc2vec两种文本向量方法，可自动输出聚类数目、类簇文档集合和簇类大小，用于自有实时数据的聚类任务。

wordninja. Probabilistically split concatenated words using NLP based on English Wikipedia unigram frequencies.

PaddleOCR. Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

UER-py. Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo

BERT-KPE. Python

lac. 百度NLP：分词，词性标注，命名实体识别，词重要性

TextAttack. TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/

Jiagu. Jiagu深度学习自然语言处理工具 知识图谱关系抽取 中文分词 词性标注 命名实体识别 情感分析 新词发现 关键词 文本摘要 文本聚类

Chinese-Text-Classification-Pytorch. 中文文本分类，TextCNN，TextRNN，FastText，TextRCNN，BiLSTM_Attention，DPCNN，Transformer，基于pytorch，开箱即用。

CPM-1-Generate. Chinese Pre-Trained Language Models (CPM-LM) Version-I