{"id":15601010,"url":"https://github.com/lucidrains/remixer-pytorch","last_synced_at":"2025-04-30T17:41:34.670Z","repository":{"id":57461049,"uuid":"410003891","full_name":"lucidrains/remixer-pytorch","owner":"lucidrains","description":"Implementation of the Remixer Block from the Remixer paper, in Pytorch","archived":false,"fork":false,"pushed_at":"2021-09-27T21:52:26.000Z","size":83,"stargazers_count":35,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-04-19T07:47:16.949Z","etag":null,"topics":["artificial-intelligence","deep-learning","transformers"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/lucidrains.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":"2021-09-24T14:58:29.000Z","updated_at":"2024-10-05T20:02:47.000Z","dependencies_parsed_at":"2022-09-17T08:11:03.835Z","dependency_job_id":null,"html_url":"https://github.com/lucidrains/remixer-pytorch","commit_stats":null,"previous_names":[],"tags_count":4,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2Fremixer-pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2Fremixer-pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2Fremixer-pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2Fremixer-pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lucidrains","download_url":"https://codeload.github.com/lucidrains/remixer-pytorch/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251752706,"owners_count":21638161,"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":["artificial-intelligence","deep-learning","transformers"],"created_at":"2024-10-03T02:11:35.524Z","updated_at":"2025-04-30T17:41:34.637Z","avatar_url":"https://github.com/lucidrains.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cimg src=\"./remixer.png\" width=\"400px\"\u003e\u003c/img\u003e\n\n## Remixer - Pytorch\n\nImplementation of the Remixer Block from the \u003ca href=\"https://openreview.net/pdf?id=9FHQHJnRtfL\"\u003eRemixer paper\u003c/a\u003e, in Pytorch. It claims that substituting the feedforwards in transformers with sequence wide mixing followed by multiplication and subtraction leads to better language understanding results.\n\n\n## Install\n\n```bash\n$ pip install remixer-pytorch\n```\n\n## Usage\n\n```python\nimport torch\nfrom remixer_pytorch import RemixerBlock\n\nblock = RemixerBlock(\n    dim = 512,\n    seq_len = 1024\n)\n\nx = torch.randn(1, 1024, 512)\nblock(x) # (1, 1024, 512)\n```\n\n## Citations\n\n```bibtex\n@inproceedings{anonymous,\n    title   = {Remixers: A Mixer-Transformer Architecture with Compositional Operators for Natural Language Understanding },\n    author  = {Anonymous},\n    year = {2021},\n    url = {https://openreview.net/forum?id=9FHQHJnRtfL}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flucidrains%2Fremixer-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flucidrains%2Fremixer-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flucidrains%2Fremixer-pytorch/lists"}