{"id":20096595,"url":"https://github.com/hendrycks/gelus","last_synced_at":"2025-05-06T05:31:48.579Z","repository":{"id":101491076,"uuid":"62731913","full_name":"hendrycks/GELUs","owner":"hendrycks","description":"A smoother activation function (undergrad code)","archived":false,"fork":false,"pushed_at":"2020-06-23T21:15:30.000Z","size":8993,"stargazers_count":109,"open_issues_count":1,"forks_count":20,"subscribers_count":6,"default_branch":"master","last_synced_at":"2025-04-09T08:51:17.003Z","etag":null,"topics":[],"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/hendrycks.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}},"created_at":"2016-07-06T15:26:02.000Z","updated_at":"2025-04-04T09:12:54.000Z","dependencies_parsed_at":null,"dependency_job_id":"cd9e1c24-0266-4056-8aa3-ef49936dae0b","html_url":"https://github.com/hendrycks/GELUs","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/hendrycks%2FGELUs","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hendrycks%2FGELUs/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hendrycks%2FGELUs/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hendrycks%2FGELUs/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hendrycks","download_url":"https://codeload.github.com/hendrycks/GELUs/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252629079,"owners_count":21779138,"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":"2024-11-13T16:59:18.060Z","updated_at":"2025-05-06T05:31:43.568Z","avatar_url":"https://github.com/hendrycks.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Gaussian Error Linear Units (GELUs)\nThis software allows users to reproduce the results in Gaussian Error Linear Units (GELUs), Dan Hendrycks and Kevin Gimpel 2016.\n\n# GELU Approximations\nThe `sigmoid(1.702 * x) * x` approximation is fast but is somewhat inaccurate. Meanwhile `0.5 * x * (1 + tanh(x * 0.7978845608 * (1 + 0.044715 * x * x)))` is slower but more accurate.\n\nHowever, exact versions are now available in pytorch, so approximations are no longer necessary for suitable speed.\n\n# Execution\nPlease install Tensorflow, Lasagne, and Python 3+.\n\n## Citation\n\nIf you find this useful in your research, please consider citing:\n\n    @article{hendrycks2016gelu,\n      title={Gaussian Error Linear Units (GELUs)},\n      author={Hendrycks, Dan and Gimpel, Kevin},\n      journal={arXiv preprint arXiv:1606.08415},\n      year={2016}\n    }\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhendrycks%2Fgelus","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhendrycks%2Fgelus","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhendrycks%2Fgelus/lists"}