{"id":13534947,"url":"https://github.com/kimiyoung/transformer-xl","last_synced_at":"2025-04-02T00:31:20.020Z","repository":{"id":37396715,"uuid":"164642888","full_name":"kimiyoung/transformer-xl","owner":"kimiyoung","description":null,"archived":false,"fork":false,"pushed_at":"2022-09-21T06:22:01.000Z","size":115,"stargazers_count":3611,"open_issues_count":97,"forks_count":763,"subscribers_count":84,"default_branch":"master","last_synced_at":"2024-11-02T22:32:55.168Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/kimiyoung.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":"2019-01-08T12:20:24.000Z","updated_at":"2024-10-22T22:00:56.000Z","dependencies_parsed_at":"2022-07-08T16:47:10.618Z","dependency_job_id":null,"html_url":"https://github.com/kimiyoung/transformer-xl","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kimiyoung%2Ftransformer-xl","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kimiyoung%2Ftransformer-xl/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kimiyoung%2Ftransformer-xl/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kimiyoung%2Ftransformer-xl/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kimiyoung","download_url":"https://codeload.github.com/kimiyoung/transformer-xl/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246735041,"owners_count":20825212,"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":[],"created_at":"2024-08-01T08:00:47.437Z","updated_at":"2025-04-02T00:31:20.011Z","avatar_url":"https://github.com/kimiyoung.png","language":"Python","funding_links":[],"categories":["improvement over BERT:","Transformer Implementations By Communities","Python","Natural Language Processing (NLP)","Feature Extraction","PyTorch Models","Paper implementations｜论文实现","Paper implementations"],"sub_categories":["TensorFlow","Notable Projects","Text/NLP","Natural Language Processing","Other libraries｜其他库:","Other libraries:"],"readme":"# Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context\n\nThis repository contains the code in both **PyTorch** and **TensorFlow** for our paper\n\u003e[Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](http://arxiv.org/abs/1901.02860)\n\n\u003eZihang Dai\\*, Zhilin Yang\\*, Yiming Yang, Jaime Carbonell, Quoc V. Le, Ruslan Salakhutdinov (*: equal contribution)\n\n\u003ePreprint 2018\n\n## TensorFlow\n\n- The source code is in the `tf/` folder, supporting (1) single-node multi-gpu training, and (2) multi-host TPU training.\n- Besides the source code, we also provide pretrained \"TensorFlow\" models with state-of-the-art (SoTA) performances reported in the paper.\n- Please refer to `tf/README.md` for details.\n\n## PyTorch\n\n- The source code is in the `pytorch/` folder, supporting single-node multi-gpu training via the module `nn.DataParallel`.\n- Please refer to `pytorch/README.md` for details.\n\n## Results\n\nTransformer-XL achieves new state-of-the-art results on multiple language modeling benchmarks. Transformer-XL is also the first to break through the 1.0 barrier on char-level language modeling. Below is a summary.\n\nMethod | enwiki8 | text8 | One Billion Word | WT-103 | PTB (w/o finetuning)\n-- | -- | -- | -- | -- | -- \nPrevious Best | 1.06 | 1.13 | 23.7 | 20.5 | 55.5\nTransformer-XL | **0.99** | **1.08** | **21.8** | **18.3** | **54.5**\n\n\n\n## Acknowledgement\n\nA large portion of the `getdata.sh` script comes from the [awd-lstm](https://github.com/salesforce/awd-lstm-lm/) repo. Happy Language Modeling :)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkimiyoung%2Ftransformer-xl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkimiyoung%2Ftransformer-xl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkimiyoung%2Ftransformer-xl/lists"}