{"id":19465194,"url":"https://github.com/luozhouyang/transformers-keras","last_synced_at":"2025-10-28T23:01:58.527Z","repository":{"id":44877205,"uuid":"185184913","full_name":"luozhouyang/transformers-keras","owner":"luozhouyang","description":"Transformer-based models implemented in tensorflow 2.x(using keras).","archived":false,"fork":false,"pushed_at":"2021-11-23T02:39:01.000Z","size":713,"stargazers_count":75,"open_issues_count":1,"forks_count":13,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-04-03T19:40:15.816Z","etag":null,"topics":["albert","bert","masked-language-models","ner","question-answering","sequence-classification","sequence-labeling","simcse","tensorflow-keras","text-classification","token-classification"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/luozhouyang.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2019-05-06T11:39:29.000Z","updated_at":"2024-07-16T04:03:56.000Z","dependencies_parsed_at":"2022-08-25T17:03:19.722Z","dependency_job_id":null,"html_url":"https://github.com/luozhouyang/transformers-keras","commit_stats":null,"previous_names":[],"tags_count":26,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/luozhouyang%2Ftransformers-keras","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/luozhouyang%2Ftransformers-keras/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/luozhouyang%2Ftransformers-keras/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/luozhouyang%2Ftransformers-keras/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/luozhouyang","download_url":"https://codeload.github.com/luozhouyang/transformers-keras/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250790142,"owners_count":21487756,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["albert","bert","masked-language-models","ner","question-answering","sequence-classification","sequence-labeling","simcse","tensorflow-keras","text-classification","token-classification"],"created_at":"2024-11-10T18:19:08.881Z","updated_at":"2025-10-28T23:01:58.433Z","avatar_url":"https://github.com/luozhouyang.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# transformers-keras\n\n![Python package](https://github.com/luozhouyang/transformers-keras/workflows/Python%20package/badge.svg)\n[![PyPI version](https://badge.fury.io/py/transformers-keras.svg)](https://badge.fury.io/py/transformers-keras)\n[![Python](https://img.shields.io/pypi/pyversions/transformers-keras.svg?style=plastic)](https://badge.fury.io/py/transformers-keras)\n\n\n基于`tf.keras`的Transformers系列模型实现。\n\n所有的`Model`都是keras模型，可以直接用于训练模型、评估模型或者导出模型用于部署。\n\n在线文档：[transformers-keras文档](https://transformers-keras.readthedocs.io/zh_CN/latest/index.html)\n\n本库功能预览：\n\n* 加载各种预训练模型的权重\n* 掩码语言模型(Masked Language Model)解决方案\n* 句向量(Sentence Embedding)的解决方案\n* 抽取式问答任务(Question Answering)的解决方案\n* 序列分类任务(Sequence Classification)的解决方案\n* 序列标注任务(Token Classification)的解决方案\n* 知识蒸馏(Knowledge Distillation)的框架\n\n以上任务的数据处理、模型构建都完成了，可以一键开始训练。这里有两个例子：\n\n* [使用BERT微调文本分类任务](https://transformers-keras.readthedocs.io/zh_CN/latest/start.html#id4)\n* [使用BERT微调问答任务](https://transformers-keras.readthedocs.io/zh_CN/latest/start.html#id5)\n\n\n更多使用方法和介绍，请查看在线文档：[transformers-keras文档](https://transformers-keras.readthedocs.io/zh_CN/latest/index.html)\n\n\n## 联系方式\n\n\u003e 由于二维码过期限制，加微信讨论群请先加我微信邀请加入。\n\n* 微信: luozhouyang0528\n* 邮箱: zhouyang.luo@gmail.com\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fluozhouyang%2Ftransformers-keras","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fluozhouyang%2Ftransformers-keras","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fluozhouyang%2Ftransformers-keras/lists"}