{"id":15601085,"url":"https://github.com/lucidrains/pause-transformer","last_synced_at":"2025-04-30T07:21:19.886Z","repository":{"id":201028358,"uuid":"706792220","full_name":"lucidrains/pause-transformer","owner":"lucidrains","description":"Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount of time on any token","archived":false,"fork":false,"pushed_at":"2023-10-22T16:41:27.000Z","size":675,"stargazers_count":42,"open_issues_count":0,"forks_count":0,"subscribers_count":4,"default_branch":"main","last_synced_at":"2024-05-02T01:14:22.661Z","etag":null,"topics":["adaptive-computation","artificial-intelligence","attention-mechanisms","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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-10-18T16:14:12.000Z","updated_at":"2024-04-15T14:30:08.000Z","dependencies_parsed_at":null,"dependency_job_id":"859edfd6-a273-413c-9710-f965a758aad4","html_url":"https://github.com/lucidrains/pause-transformer","commit_stats":null,"previous_names":["lucidrains/pause-transformer"],"tags_count":7,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2Fpause-transformer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2Fpause-transformer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2Fpause-transformer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2Fpause-transformer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lucidrains","download_url":"https://codeload.github.com/lucidrains/pause-transformer/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246326595,"owners_count":20759436,"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":["adaptive-computation","artificial-intelligence","attention-mechanisms","deep-learning","transformers"],"created_at":"2024-10-03T02:14:15.175Z","updated_at":"2025-03-31T13:31:05.667Z","avatar_url":"https://github.com/lucidrains.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cimg src=\"./pause.png\" width=\"400px\"\u003e\u003c/img\u003e\n\n## Pause Transformer (wip)\n\nYet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount of time on any token.\n\nAgain, the idea relies on axial attention; one axis attends along the sequence length as in the usual transformer, the other along a `thinking` or `pause` dimension.\n\n## Todo\n\n- [x] allow for custom pause distributions across token\n- [x] see if one can do a two pass, using the logit entropy as a way to decide how to shape the pause mask\n\n- [ ] run experiments on enwik8, but if do not see anything, move onwards to something harder, say arithmetic\n\n## Citations\n\n```bibtex\n@inproceedings{Goyal2023ThinkBY,\n    title   = {Think before you speak: Training Language Models With Pause Tokens},\n    author  = {Sachin Goyal and Ziwei Ji and Ankit Singh Rawat and Aditya Krishna Menon and Sanjiv Kumar and Vaishnavh Nagarajan},\n    year    = {2023},\n    url     = {https://api.semanticscholar.org/CorpusID:263608983}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flucidrains%2Fpause-transformer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flucidrains%2Fpause-transformer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flucidrains%2Fpause-transformer/lists"}