Top 100 Transformer Repositories
Ranking
| Ranking | Project Name | Stars | Forks | Language | Open Issues | Description | Last Commit |
|---|---|---|---|---|---|---|---|
| 1 | transformers | 160,787 | 33,275 | Python | 1037 | 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. | 2026-05-20 |
| 2 | funNLP | 80,753 | 15,219 | Python | 38 | 中英文敏感词、语言检测、中外手机/电话归属地/运营商查询、名字推断性别、手机号抽取、身份证抽取、邮箱抽取、中日文人名库、中文缩写库、拆字词典、词汇情感值、停用词、反动词表、暴恐词表、繁简体转换、英文模拟中文发音、汪峰歌词生成器、职业名称词库、同义词库、反义词库、否定词库、汽车品牌词库、汽车零件词库、连续英文切割、各种中文词向量、公司名字大全、古诗词库、IT词库、财经词库、成语词库、地名词库、历史名人词库、诗词词库、医学词库、饮食词库、法律词库、汽车词库、动物词库、中文聊天语料、中文谣言数据、百度中文问答数据集、句子相似度匹配算法集合、bert资源、文本生成&摘要相关工具、cocoNLP信息抽取工具、国内电话号码正则匹配、清华大学XLORE:中英文跨语言百科知识图谱、清华大学人工智能技术系列报告、自然语言生成、NLU太难了系列、自动对联数据及机器人、用户名黑名单列表、罪名法务名词及分类模型、微信公众号语料、cs224n深度学习自然语言处理课程、中文手写汉字识别、中文自然语言处理 语料/数据集、变量命名神器、分词语料库+代码、任务型对话英文数据集、ASR 语音数据集 + 基于深度学习的中文语音识别系统、笑声检测器、Microsoft多语言数字/单位/如日期时间识别包、中华新华字典数据库及api(包括常用歇后语、成语、词语和汉字)、文档图谱自动生成、SpaCy 中文模型、Common Voice语音识别数据集新版、神经网络关系抽取、基于bert的命名实体识别、关键词(Keyphrase)抽取包pke、基于医疗领域知识图谱的问答系统、基于依存句法与语义角色标注的事件三元组抽取、依存句法分析4万句高质量标注数据、cnocr：用来做中文OCR的Python3包、中文人物关系知识图谱项目、中文nlp竞赛项目及代码汇总、中文字符数据、speech-aligner: 从“人声语音”及其“语言文本”产生音素级别时间对齐标注的工具、AmpliGraph: 知识图谱表示学习(Python)库：知识图谱概念链接预测、Scattertext 文本可视化(python)、语言/知识表示工具：BERT & ERNIE、中文对比英文自然语言处理NLP的区别综述、Synonyms中文近义词工具包、HarvestText领域自适应文本挖掘工具（新词发现-情感分析-实体链接等）、word2word：(Python)方便易用的多语言词-词对集：62种语言/3,564个多语言对、语音识别语料生成工具：从具有音频/字幕的在线视频创建自动语音识别(ASR)语料库、构建医疗实体识别的模型（包含词典和语料标注）、单文档非监督的关键词抽取、Kashgari中使用gpt-2语言模型、开源的金融投资数据提取工具、文本自动摘要库TextTeaser: 仅支持英文、人民日报语料处理工具集、一些关于自然语言的基本模型、基于14W歌曲知识库的问答尝试--功能包括歌词接龙and已知歌词找歌曲以及歌曲歌手歌词三角关系的问答、基于Siamese bilstm模型的相似句子判定模型并提供训练数据集和测试数据集、用Transformer编解码模型实现的根据Hacker News文章标题自动生成评论、用BERT进行序列标记和文本分类的模板代码、LitBank：NLP数据集——支持自然语言处理和计算人文学科任务的100部带标记英文小说语料、百度开源的基准信息抽取系统、虚假新闻数据集、Facebook: LAMA语言模型分析，提供Transformer-XL/BERT/ELMo/GPT预训练语言模型的统一访问接口、CommonsenseQA：面向常识的英文QA挑战、中文知识图谱资料、数据及工具、各大公司内部里大牛分享的技术文档 PDF 或者 PPT、自然语言生成SQL语句（英文）、中文NLP数据增强（EDA）工具、英文NLP数据增强工具 、基于医药知识图谱的智能问答系统、京东商品知识图谱、基于mongodb存储的军事领域知识图谱问答项目、基于远监督的中文关系抽取、语音情感分析、中文ULMFiT-情感分析-文本分类-语料及模型、一个拍照做题程序、世界各国大规模人名库、一个利用有趣中文语料库 qingyun 训练出来的中文聊天机器人、中文聊天机器人seqGAN、省市区镇行政区划数据带拼音标注、教育行业新闻语料库包含自动文摘功能、开放了对话机器人-知识图谱-语义理解-自然语言处理工具及数据、中文知识图谱：基于百度百科中文页面-抽取三元组信息-构建中文知识图谱、masr: 中文语音识别-提供预训练模型-高识别率、Python音频数据增广库、中文全词覆盖BERT及两份阅读理解数据、ConvLab：开源多域端到端对话系统平台、中文自然语言处理数据集、基于最新版本rasa搭建的对话系统、基于TensorFlow和BERT的管道式实体及关系抽取、一个小型的证券知识图谱/知识库、复盘所有NLP比赛的TOP方案、OpenCLaP：多领域开源中文预训练语言模型仓库、UER：基于不同语料+编码器+目标任务的中文预训练模型仓库、中文自然语言处理向量合集、基于金融-司法领域(兼有闲聊性质)的聊天机器人、g2pC：基于上下文的汉语读音自动标记模块、Zincbase 知识图谱构建工具包、诗歌质量评价/细粒度情感诗歌语料库、快速转化「中文数字」和「阿拉伯数字」、百度知道问答语料库、基于知识图谱的问答系统、jieba_fast 加速版的jieba、正则表达式教程、中文阅读理解数据集、基于BERT等最新语言模型的抽取式摘要提取、Python利用深度学习进行文本摘要的综合指南、知识图谱深度学习相关资料整理、维基大规模平行文本语料、StanfordNLP 0.2.0：纯Python版自然语言处理包、NeuralNLP-NeuralClassifier：腾讯开源深度学习文本分类工具、端到端的封闭域对话系统、中文命名实体识别：NeuroNER vs. BertNER、新闻事件线索抽取、2019年百度的三元组抽取比赛：“科学空间队”源码、基于依存句法的开放域文本知识三元组抽取和知识库构建、中文的GPT2训练代码、ML-NLP - 机器学习(Machine Learning)NLP面试中常考到的知识点和代码实现、nlp4han:中文自然语言处理工具集(断句/分词/词性标注/组块/句法分析/语义分析/NER/N元语法/HMM/代词消解/情感分析/拼写检查、XLM：Facebook的跨语言预训练语言模型、用基于BERT的微调和特征提取方法来进行知识图谱百度百科人物词条属性抽取、中文自然语言处理相关的开放任务-数据集-当前最佳结果、CoupletAI - 基于CNN+Bi-LSTM+Attention 的自动对对联系统、抽象知识图谱、MiningZhiDaoQACorpus - 580万百度知道问答数据挖掘项目、brat rapid annotation tool: 序列标注工具、大规模中文知识图谱数据：1.4亿实体、数据增强在机器翻译及其他nlp任务中的应用及效果、allennlp阅读理解:支持多种数据和模型、PDF表格数据提取工具 、 Graphbrain：AI开源软件库和科研工具，目的是促进自动意义提取和文本理解以及知识的探索和推断、简历自动筛选系统、基于命名实体识别的简历自动摘要、中文语言理解测评基准，包括代表性的数据集&基准模型&语料库&排行榜、树洞 OCR 文字识别 、从包含表格的扫描图片中识别表格和文字、语声迁移、Python口语自然语言处理工具集(英文)、 similarity：相似度计算工具包，java编写、海量中文预训练ALBERT模型 、Transformers 2.0 、基于大规模音频数据集Audioset的音频增强 、Poplar：网页版自然语言标注工具、图片文字去除，可用于漫画翻译 、186种语言的数字叫法库、Amazon发布基于知识的人-人开放领域对话数据集 、中文文本纠错模块代码、繁简体转换 、 Python实现的多种文本可读性评价指标、类似于人名/地名/组织机构名的命名体识别数据集 、东南大学《知识图谱》研究生课程(资料)、. 英文拼写检查库 、 wwsearch是企业微信后台自研的全文检索引擎、CHAMELEON：深度学习新闻推荐系统元架构 、 8篇论文梳理BERT相关模型进展与反思、DocSearch：免费文档搜索引擎、 LIDA：轻量交互式对话标注工具 、aili - the fastest in-memory index in the East 东半球最快并发索引 、知识图谱车音工作项目、自然语言生成资源大全 、中日韩分词库mecab的Python接口库、中文文本摘要/关键词提取、汉字字符特征提取器 (featurizer)，提取汉字的特征（发音特征、字形特征）用做深度学习的特征、中文生成任务基准测评 、中文缩写数据集、中文任务基准测评 - 代表性的数据集-基准(预训练)模型-语料库-baseline-工具包-排行榜、PySS3：面向可解释AI的SS3文本分类器机器可视化工具 、中文NLP数据集列表、COPE - 格律诗编辑程序、doccano：基于网页的开源协同多语言文本标注工具 、PreNLP：自然语言预处理库、简单的简历解析器，用来从简历中提取关键信息、用于中文闲聊的GPT2模型：GPT2-chitchat、基于检索聊天机器人多轮响应选择相关资源列表(Leaderboards、Datasets、Papers)、(Colab)抽象文本摘要实现集锦(教程 、词语拼音数据、高效模糊搜索工具、NLP数据增广资源集、微软对话机器人框架 、 GitHub Typo Corpus：大规模GitHub多语言拼写错误/语法错误数据集、TextCluster：短文本聚类预处理模块 Short text cluster、面向语音识别的中文文本规范化、BLINK：最先进的实体链接库、BertPunc：基于BERT的最先进标点修复模型、Tokenizer：快速、可定制的文本词条化库、中文语言理解测评基准，包括代表性的数据集、基准(预训练)模型、语料库、排行榜、spaCy 医学文本挖掘与信息提取 、 NLP任务示例项目代码集、 python拼写检查库、chatbot-list - 行业内关于智能客服、聊天机器人的应用和架构、算法分享和介绍、语音质量评价指标(MOSNet, BSSEval, STOI, PESQ, SRMR)、 用138GB语料训练的法文RoBERTa预训练语言模型 、BERT-NER-Pytorch：三种不同模式的BERT中文NER实验、无道词典 - 有道词典的命令行版本，支持英汉互查和在线查询、2019年NLP亮点回顾、 Chinese medical dialogue data 中文医疗对话数据集 、最好的汉字数字(中文数字)-阿拉伯数字转换工具、 基于百科知识库的中文词语多词义/义项获取与特定句子词语语义消歧、awesome-nlp-sentiment-analysis - 情感分析、情绪原因识别、评价对象和评价词抽取、LineFlow：面向所有深度学习框架的NLP数据高效加载器、中文医学NLP公开资源整理 、MedQuAD：(英文)医学问答数据集、将自然语言数字串解析转换为整数和浮点数、Transfer Learning in Natural Language Processing (NLP) 、面向语音识别的中文/英文发音辞典、Tokenizers：注重性能与多功能性的最先进分词器、CLUENER 细粒度命名实体识别 Fine Grained Named Entity Recognition、 基于BERT的中文命名实体识别、中文谣言数据库、NLP数据集/基准任务大列表、nlp相关的一些论文及代码, 包括主题模型、词向量(Word Embedding)、命名实体识别(NER)、文本分类(Text Classificatin)、文本生成(Text Generation)、文本相似性(Text Similarity)计算等，涉及到各种与nlp相关的算法，基于keras和tensorflow 、Python文本挖掘/NLP实战示例、 Blackstone：面向非结构化法律文本的spaCy pipeline和NLP模型通过同义词替换实现文本“变脸” 、中文 预训练 ELECTREA 模型: 基于对抗学习 pretrain Chinese Model 、albert-chinese-ner - 用预训练语言模型ALBERT做中文NER 、基于GPT2的特定主题文本生成/文本增广、开源预训练语言模型合集、多语言句向量包、编码、标记和实现：一种可控高效的文本生成方法、 英文脏话大列表 、attnvis：GPT2、BERT等transformer语言模型注意力交互可视化、CoVoST：Facebook发布的多语种语音-文本翻译语料库，包括11种语言(法语、德语、荷兰语、俄语、西班牙语、意大利语、土耳其语、波斯语、瑞典语、蒙古语和中文)的语音、文字转录及英文译文、Jiagu自然语言处理工具 - 以BiLSTM等模型为基础，提供知识图谱关系抽取 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 文本聚类等功能、用unet实现对文档表格的自动检测，表格重建、NLP事件提取文献资源列表 、 金融领域自然语言处理研究资源大列表、CLUEDatasetSearch - 中英文NLP数据集：搜索所有中文NLP数据集，附常用英文NLP数据集 、medical_NER - 中文医学知识图谱命名实体识别 、(哈佛)讲因果推理的免费书、知识图谱相关学习资料/数据集/工具资源大列表、Forte：灵活强大的自然语言处理pipeline工具集 、Python字符串相似性算法库、PyLaia：面向手写文档分析的深度学习工具包、TextFooler：针对文本分类/推理的对抗文本生成模块、Haystack：灵活、强大的可扩展问答(QA)框架、中文关键短语抽取工具 | 2024-05-10 |
| 3 | vllm | 80,512 | 16,991 | Python | 1982 | A high-throughput and memory-efficient inference and serving engine for LLMs | 2026-05-20 |
| 4 | annotated_deep_learning_paper_implementations | 66,776 | 6,715 | Python | 29 | 🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠 | 2026-01-22 |
| 5 | whisper.cpp | 49,899 | 5,552 | C++ | 1036 | Port of OpenAI's Whisper model in C/C++ | 2026-05-19 |
| 6 | pytorch-image-models | 36,822 | 5,164 | Python | 48 | 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 | 2026-05-08 |
| 7 | mmdetection | 32,700 | 9,835 | Python | 1773 | OpenMMLab Detection Toolbox and Benchmark | 2024-08-21 |
| 8 | fish-speech | 30,416 | 2,586 | Python | 12 | SOTA Open Source TTS | 2026-05-12 |
| 9 | sglang | 28,035 | 6,014 | Python | 648 | SGLang is a high-performance serving framework for large language models and multimodal models. | 2026-05-20 |
| 10 | vit-pytorch | 25,187 | 3,488 | Python | 130 | Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch | 2026-05-19 |
| 11 | minGPT | 24,412 | 3,253 | Python | 49 | A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training | 2024-08-15 |
| 12 | best-of-ml-python | 23,487 | 3,113 | - | 33 | 🏆 A ranked list of awesome machine learning Python libraries. Updated weekly. | 2026-05-14 |
| 13 | faster-whisper | 23,005 | 1,879 | Python | 282 | Faster Whisper transcription with CTranslate2 | 2025-11-19 |
| 14 | CVPR2026-Papers-with-Code | 22,571 | 2,791 | - | 8 | CVPR 2026 论文和开源项目合集 | 2026-03-08 |
| 15 | heretic | 21,078 | 2,174 | Python | 55 | Fully automatic censorship removal for language models | 2026-05-16 |
| 16 | sentence-transformers | 18,693 | 2,790 | Python | 1278 | State-of-the-Art Embeddings, Retrieval, and Reranking | 2026-05-15 |
| 17 | trl | 18,417 | 2,730 | Python | 556 | Train transformer language models with reinforcement learning. | 2026-05-19 |
| 18 | CodeFormer | 17,981 | 3,709 | Python | 262 | [NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer | 2025-11-18 |
| 19 | leedl-tutorial | 16,568 | 3,101 | Jupyter Notebook | 2 | 《李宏毅深度学习教程》（李宏毅老师推荐👍，苹果书🍎），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases | 2025-11-23 |
| 20 | Megatron-LM | 16,397 | 3,979 | Python | 361 | Ongoing research training transformer models at scale | 2026-05-20 |
| 21 | LaTeX-OCR | 16,394 | 1,302 | Python | 142 | pix2tex: Using a ViT to convert images of equations into LaTeX code. | 2025-01-18 |
| 22 | transformers.js | 16,015 | 1,142 | JavaScript | 178 | State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server! | 2026-05-18 |
| 23 | Swin-Transformer | 15,925 | 2,221 | Python | 186 | This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows". | 2024-07-24 |
| 24 | detr | 15,276 | 2,668 | Python | 240 | End-to-End Object Detection with Transformers | 2024-03-12 |
| 25 | MNN | 15,194 | 2,314 | C++ | 5 | MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI. | 2026-05-20 |
| 26 | nlp-tutorial | 14,896 | 3,952 | Jupyter Notebook | 34 | Natural Language Processing Tutorial for Deep Learning Researchers | 2024-02-21 |
| 27 | RWKV-LM | 14,534 | 1,010 | Python | 122 | RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding. | 2026-05-08 |
| 28 | nano-vllm | 13,517 | 2,111 | Python | 26 | Nano vLLM | 2026-04-26 |
| 29 | vggt | 13,143 | 1,464 | Python | 246 | [CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer | 2026-05-19 |
| 30 | dio | 12,815 | 1,556 | Dart | 27 | A powerful HTTP client for Dart and Flutter, which supports global settings, Interceptors, FormData, aborting and canceling a request, files uploading and downloading, requests timeout, custom adapters, etc. | 2026-05-19 |
| 31 | pytorch-grad-cam | 12,812 | 1,705 | Python | 153 | Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more. | 2026-04-25 |
| 32 | lm-evaluation-harness | 12,625 | 3,277 | Python | 565 | A framework for few-shot evaluation of language models. | 2026-05-11 |
| 33 | PaddleSpeech | 12,601 | 1,954 | Python | 265 | Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award. | 2026-05-07 |
| 34 | vision_transformer | 12,533 | 1,468 | Jupyter Notebook | 127 | 2026-03-03 | |
| 35 | Transformers-Tutorials | 11,628 | 1,718 | Jupyter Notebook | 304 | This repository contains demos I made with the Transformers library by HuggingFace. | 2026-04-20 |
| 36 | segmentation_models.pytorch | 11,562 | 1,837 | Python | 70 | Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones. | 2026-05-19 |
| 37 | text-generation-inference | 10,856 | 1,271 | Python | 285 | Large Language Model Text Generation Inference | 2026-03-21 |
| 38 | xformers | 10,463 | 773 | Python | 365 | Hackable and optimized Transformers building blocks, supporting a composable construction. | 2026-04-21 |
| 39 | petals | 10,140 | 609 | Python | 92 | 🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading | 2024-09-07 |
| 40 | manga-image-translator | 9,920 | 993 | Python | 133 | Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/ (no longer working) | 2026-05-19 |
| 41 | mmsegmentation | 9,806 | 2,841 | Python | 772 | OpenMMLab Semantic Segmentation Toolbox and Benchmark. | 2024-08-13 |
| 42 | attention-is-all-you-need-pytorch | 9,726 | 2,095 | Python | 66 | A PyTorch implementation of the Transformer model in "Attention is All You Need". | 2024-04-16 |
| 43 | PaddleSeg | 9,326 | 1,710 | Python | 24 | Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image Matting, 3D Segmentation, etc. | 2026-02-05 |
| 44 | DiT | 8,580 | 790 | Python | 67 | Official PyTorch Implementation of "Scalable Diffusion Models with Transformers" | 2024-05-31 |
| 45 | LMFlow | 8,485 | 832 | Python | 77 | An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All. | 2026-05-07 |
| 46 | trax | 8,303 | 824 | Python | 107 | Trax — Deep Learning with Clear Code and Speed | 2025-09-26 |
| 47 | bertviz | 8,064 | 879 | Python | 21 | BertViz: Visualize Attention in Transformer Models | 2026-01-08 |
| 48 | jukebox | 8,038 | 1,451 | Python | 194 | Code for the paper "Jukebox: A Generative Model for Music" | 2024-06-19 |
| 49 | GPT2-Chinese | 7,601 | 1,688 | Python | 101 | Chinese version of GPT2 training code, using BERT tokenizer. | 2024-04-25 |
| 50 | dino | 7,567 | 1,041 | Python | 101 | PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO | 2024-07-03 |
| 51 | transformer-explainer | 7,551 | 820 | JavaScript | 8 | Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization | 2026-05-14 |
| 52 | lightningcss | 7,539 | 268 | Rust | 329 | An extremely fast CSS parser, transformer, bundler, and minifier written in Rust. | 2026-05-19 |
| 53 | gpt-neox | 7,429 | 1,114 | Python | 61 | An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries | 2026-05-19 |
| 54 | class-transformer | 7,331 | 518 | TypeScript | 209 | Decorator-based transformation, serialization, and deserialization between objects and classes. | 2026-04-02 |
| 55 | annotated-transformer | 7,263 | 1,542 | Jupyter Notebook | 31 | An annotated implementation of the Transformer paper. | 2024-04-07 |
| 56 | ts-jest | 7,077 | 476 | TypeScript | 70 | A Jest transformer with source map support that lets you use Jest to test projects written in TypeScript. | 2026-05-19 |
| 57 | Sana | 7,055 | 510 | Python | 105 | SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer | 2026-05-18 |
| 58 | donut | 6,869 | 560 | Python | 207 | Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022 | 2024-07-11 |
| 59 | MindSearch | 6,862 | 681 | JavaScript | 47 | 🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT) | 2025-07-04 |
| 60 | ProPainter | 6,693 | 791 | Python | 72 | [ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting | 2025-02-19 |
| 61 | BERT-pytorch | 6,534 | 1,320 | Python | 58 | Google AI 2018 BERT pytorch implementation | 2023-09-15 |
| 62 | text-to-text-transfer-transformer | 6,517 | 794 | Python | 59 | Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer" | 2026-01-14 |
| 63 | Informer2020 | 6,491 | 1,288 | Python | 184 | The GitHub repository for the paper "Informer" accepted by AAAI 2021. | 2025-06-20 |
| 64 | taming-transformers | 6,490 | 1,223 | Jupyter Notebook | 147 | Taming Transformers for High-Resolution Image Synthesis | 2024-07-30 |
| 65 | FasterTransformer | 6,415 | 935 | C++ | 249 | Transformer related optimization, including BERT, GPT | 2024-03-27 |
| 66 | mesh-transformer-jax | 6,369 | 884 | Python | 49 | Model parallel transformers in JAX and Haiku | 2023-01-21 |
| 67 | gpt-fast | 6,210 | 572 | Python | 76 | Simple and efficient pytorch-native transformer text generation in <1000 LOC of python. | 2025-08-22 |
| 68 | gogocode | 6,085 | 461 | JavaScript | 90 | GoGoCode is a transformer for JavaScript/Typescript/HTML based on AST but providing a more intuitive API. | 2024-04-11 |
| 69 | tsai | 6,064 | 717 | Jupyter Notebook | 108 | Time series Timeseries Deep Learning Machine Learning Python Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai | 2026-05-13 |
| 70 | Awesome-Prompt-Engineering | 5,933 | 674 | TypeScript | 5 | This repository contains a hand-curated resources for Prompt Engineering with a focus on Generative Pre-trained Transformer (GPT), ChatGPT, PaLM etc | 2026-05-19 |
| 71 | x-transformers | 5,861 | 509 | Python | 71 | A concise but complete full-attention transformer with a set of promising experimental features from various papers | 2026-05-19 |
| 72 | Chinese-Text-Classification-Pytorch | 5,734 | 1,267 | Python | 80 | 中文文本分类，TextCNN，TextRNN，FastText，TextRCNN，BiLSTM_Attention，DPCNN，Transformer，基于pytorch，开箱即用。 | 2020-09-23 |
| 73 | pytorch-seq2seq | 5,692 | 1,358 | Jupyter Notebook | 7 | Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText. | 2024-01-20 |
| 74 | DALLE-pytorch | 5,629 | 643 | Python | 120 | Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch | 2024-02-17 |
| 75 | SwinIR | 5,485 | 654 | Python | 72 | SwinIR: Image Restoration Using Swin Transformer (official repository) | 2024-05-14 |
| 76 | bert4keras | 5,422 | 924 | Python | 165 | keras implement of transformers for humans | 2024-11-11 |
| 77 | understand-prompt | 5,362 | 436 | Jupyter Notebook | 0 | 【🔞🔞🔞 内含不适合未成年人阅读的图片】基于我擅长的编程、绘画、写作展开的 AI 探索和总结：StableDiffusion 是一种强大的图像生成模型，能够通过对一张图片进行演化来生成新的图片。ChatGPT 是一个基于 Transformer 的语言生成模型，它能够自动为输入的主题生成合适的文章。而 Github Copilot 是一个智能编程助手，能够加速日常编程活动。 | 2023-03-11 |
| 78 | recast | 5,238 | 359 | TypeScript | 169 | JavaScript syntax tree transformer, nondestructive pretty-printer, and automatic source map generator | 2025-03-03 |
| 79 | RT-DETR | 5,216 | 610 | Python | 410 | [CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥 | 2026-03-02 |
| 80 | cactus | 5,152 | 407 | C | 16 | Low-latency AI engine for mobile devices & wearables | 2026-05-20 |
| 81 | wenet | 5,120 | 1,182 | Python | 1 | Production First and Production Ready End-to-End Speech Recognition Toolkit | 2026-05-11 |
| 82 | qpdf | 5,065 | 378 | C++ | 137 | qpdf: A content-preserving PDF document transformer | 2026-05-12 |
| 83 | AutoGPTQ | 5,061 | 543 | Python | 241 | An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm. | 2025-04-11 |
| 84 | Awesome-Transformer-Attention | 5,034 | 496 | - | 3 | An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites | 2024-07-30 |
| 85 | transformerlab-app | 4,945 | 511 | Python | 21 | The open source research environment for AI researchers to seamlessly train, evaluate, and scale models from local hardware to GPU clusters. | 2026-05-20 |
| 86 | OpenPrompt | 4,869 | 483 | Python | 87 | An Open-Source Framework for Prompt-Learning. | 2024-07-16 |
| 87 | vllm-omni | 4,816 | 956 | Python | 445 | A framework for efficient model inference with omni-modality models | 2026-05-20 |
| 88 | notebooks | 4,771 | 1,468 | Jupyter Notebook | 83 | Jupyter notebooks for the Natural Language Processing with Transformers book | 2024-08-21 |
| 89 | beatai | 4,664 | 254 | JavaScript | 2 | 🦄 不玩晦涩不搞少数派的 AI 入门圣经，从学生到工程师都能轻松掌握。涵盖神经网络到大模型、顶层设计到微观原理、工程实现到算法基础。 学完后，大家能彻底看懂为什么下一 token 预测这个看似不起眼的能力可以改变世界，也能发现原来 AI 并没有想象中那么神秘、那么高不可攀。 Let's just beat it ! | 2026-05-20 |
| 90 | transformer | 4,573 | 634 | Python | 15 | Transformer: PyTorch Implementation of "Attention Is All You Need" | 2025-07-15 |
| 91 | CTranslate2 | 4,492 | 488 | C++ | 219 | Fast inference engine for Transformer models | 2026-05-19 |
| 92 | transformer | 4,472 | 1,302 | Python | 126 | A TensorFlow Implementation of the Transformer: Attention Is All You Need | 2023-05-21 |
| 93 | primus | 4,472 | 269 | JavaScript | 50 | ⚡ Primus, the creator god of the transformers & an abstraction layer for real-time to prevent module lock-in. | 2023-11-06 |
| 94 | Efficient-AI-Backbones | 4,414 | 737 | Python | 93 | Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab. | 2025-03-15 |
| 95 | stanford-cme-295-transformers-large-language-models | 4,405 | 623 | - | 8 | VIP cheatsheet for Stanford's CME 295 Transformers and Large Language Models | 2025-07-27 |
| 96 | HunyuanDiT | 4,296 | 361 | Jupyter Notebook | 102 | Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding | 2025-11-27 |
| 97 | simpletransformers | 4,245 | 717 | Python | 45 | Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI | 2025-08-25 |
| 98 | neuralforecast | 4,126 | 488 | Python | 42 | Scalable and user friendly neural 🧠 forecasting algorithms. | 2026-05-19 |
| 99 | transformer-debugger | 4,113 | 238 | Python | 9 | 2026-04-15 | |
| 100 | transformers-code | 3,974 | 517 | Jupyter Notebook | 4 | 手把手带你实战 Huggingface Transformers 课程视频同步更新在B站与YouTube | 2024-07-15 |