{"payload":{"feedbackUrl":"https://github.com/orgs/community/discussions/53140","repo":{"id":734117107,"defaultBranch":"main","name":"cookbook","ownerLogin":"EleutherAI","currentUserCanPush":false,"isFork":false,"isEmpty":false,"createdAt":"2023-12-20T23:01:54.000Z","ownerAvatar":"https://avatars.githubusercontent.com/u/68924597?v=4","public":true,"private":false,"isOrgOwned":true},"refInfo":{"name":"","listCacheKey":"v0:1723478859.0","currentOid":""},"activityList":{"items":[{"before":"d6e9d97fb77c712ba2c82d37cfa559240345945b","after":"efb225c7e932fa3c21a769f39792b71c585c3478","ref":"refs/heads/main","pushedAt":"2024-08-19T16:42:20.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"Quentin-Anthony","name":"Quentin Anthony","path":"/Quentin-Anthony","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/10281105?s=80&v=4"},"commit":{"message":"Add HuggingFace arg so that arch is automatic (#39)\n\n* Add placeholder fn get_hf_model_args()\r\n\r\n* Update the fn get_args_from_hf\r\n\r\n* Remove stale comments\r\n\r\n* chore: Set default values for arguments in calc_transformer_mem.py\r\n\r\n* Add placeholder fn get_hf_model_args()\r\n\r\n* Update the fn get_args_from_hf\r\n\r\n* Remove stale comments\r\n\r\n* chore: Set default values for arguments in calc_transformer_mem.py\r\n\r\n* Clean up and rebase\r\n\r\n* update mem calc readme with hf arg\r\n\r\n* add Bhavnick as calc mem author\r\n\r\n---------\r\n\r\nCo-authored-by: Quentin Anthony ","shortMessageHtmlLink":"Add HuggingFace arg so that arch is automatic (#39)"}},{"before":"040eca588b95f045ee14e462ec4d12bbfd483641","after":"d6e9d97fb77c712ba2c82d37cfa559240345945b","ref":"refs/heads/main","pushedAt":"2024-08-19T15:56:16.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"Quentin-Anthony","name":"Quentin Anthony","path":"/Quentin-Anthony","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/10281105?s=80&v=4"},"commit":{"message":"--swiglu conflicts with --num-mlp-linears (#44)","shortMessageHtmlLink":"--swiglu conflicts with --num-mlp-linears (#44)"}},{"before":"a7bcd314de357f67e0ca9c7a640f1446c92e9487","after":"040eca588b95f045ee14e462ec4d12bbfd483641","ref":"refs/heads/main","pushedAt":"2024-08-19T15:52:20.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"Quentin-Anthony","name":"Quentin Anthony","path":"/Quentin-Anthony","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/10281105?s=80&v=4"},"commit":{"message":"Add transformer explainer","shortMessageHtmlLink":"Add transformer explainer"}},{"before":null,"after":"ad9a859719af2ce1d2d9dd6658ad1a1777e89f5a","ref":"refs/heads/better-glu-args","pushedAt":"2024-08-12T16:07:39.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"haileyschoelkopf","name":"Hailey Schoelkopf","path":"/haileyschoelkopf","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/65563625?s=80&v=4"},"commit":{"message":"--swiglu conflicts with --num-mlp-linears","shortMessageHtmlLink":"--swiglu conflicts with --num-mlp-linears"}},{"before":"685de193d24da86beeb2d2cef060105722854da7","after":"a7bcd314de357f67e0ca9c7a640f1446c92e9487","ref":"refs/heads/main","pushedAt":"2024-08-11T14:56:40.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"Quentin-Anthony","name":"Quentin Anthony","path":"/Quentin-Anthony","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/10281105?s=80&v=4"},"commit":{"message":"cleanup","shortMessageHtmlLink":"cleanup"}},{"before":"ee051ec0606f2965d88bf0c150bc2b09ace345c6","after":"685de193d24da86beeb2d2cef060105722854da7","ref":"refs/heads/main","pushedAt":"2024-08-11T12:28:58.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"Quentin-Anthony","name":"Quentin Anthony","path":"/Quentin-Anthony","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/10281105?s=80&v=4"},"commit":{"message":"remove duplicate ffn expansion factor arg from flops calc","shortMessageHtmlLink":"remove duplicate ffn expansion factor arg from flops calc"}},{"before":"a17c66f6d20d711c43f9cb60013a7eb2c29245ef","after":"ee051ec0606f2965d88bf0c150bc2b09ace345c6","ref":"refs/heads/main","pushedAt":"2024-08-11T12:27:51.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"Quentin-Anthony","name":"Quentin Anthony","path":"/Quentin-Anthony","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/10281105?s=80&v=4"},"commit":{"message":"Add missing `--ffn-expansion-factor` to FLOPs calculator script (#35)\n\n* add ffn-expansion-factor to flops script\r\n\r\n* Update calc_transformer_flops.py\r\n\r\n---------\r\n\r\nCo-authored-by: Quentin Anthony ","shortMessageHtmlLink":"Add missing --ffn-expansion-factor to FLOPs calculator script (#35)"}},{"before":"a69d4071ea5d200a24325762a39683cbbe274087","after":"4792ad99379d566bba4eb156f9c48a46b738738b","ref":"refs/heads/ffn-expansion","pushedAt":"2024-08-11T12:21:45.000Z","pushType":"push","commitsCount":4,"pusher":{"login":"Quentin-Anthony","name":"Quentin Anthony","path":"/Quentin-Anthony","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/10281105?s=80&v=4"},"commit":{"message":"Merge branch 'main' into ffn-expansion","shortMessageHtmlLink":"Merge branch 'main' into ffn-expansion"}},{"before":"d4ca9a01e6cd35ed6ddd425392c912267f5af3e4","after":"a17c66f6d20d711c43f9cb60013a7eb2c29245ef","ref":"refs/heads/main","pushedAt":"2024-08-11T12:17:37.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"Quentin-Anthony","name":"Quentin Anthony","path":"/Quentin-Anthony","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/10281105?s=80&v=4"},"commit":{"message":"Add MLP Linears Argument (#37)\n\n* Add mlp linears arg and clean up args indentation\r\n\r\n* add linears per mlp and expansion factor args to flop calculation\r\n\r\n* add updated options to calc readme","shortMessageHtmlLink":"Add MLP Linears Argument (#37)"}},{"before":"02edb7ee7c2686173cbfc2e4f370f62e6f93f497","after":"f8086794a76744b318456ea650f729ea6b50f50a","ref":"refs/heads/qanthony/mlp_linears","pushedAt":"2024-08-11T12:16:16.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"Quentin-Anthony","name":"Quentin Anthony","path":"/Quentin-Anthony","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/10281105?s=80&v=4"},"commit":{"message":"add updated options to calc readme","shortMessageHtmlLink":"add updated options to calc readme"}},{"before":"8e7954fdb34ed4e73f0747a06cef51eb65615270","after":"02edb7ee7c2686173cbfc2e4f370f62e6f93f497","ref":"refs/heads/qanthony/mlp_linears","pushedAt":"2024-08-11T12:13:22.000Z","pushType":"push","commitsCount":3,"pusher":{"login":"Quentin-Anthony","name":"Quentin Anthony","path":"/Quentin-Anthony","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/10281105?s=80&v=4"},"commit":{"message":"Merge branch 'main' into qanthony/mlp_linears","shortMessageHtmlLink":"Merge branch 'main' into qanthony/mlp_linears"}},{"before":"86ff050b6432bb423eb20cb7770ca7dbdcef6f48","after":"d4ca9a01e6cd35ed6ddd425392c912267f5af3e4","ref":"refs/heads/main","pushedAt":"2024-08-11T12:11:46.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"Quentin-Anthony","name":"Quentin Anthony","path":"/Quentin-Anthony","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/10281105?s=80&v=4"},"commit":{"message":"Add tied embeddings and output tokens option (#41)\n\n* Add tied embedding option\r\n\r\n* update readme with new tied embedding flag\r\n\r\n* add output tokens to kv-mem calc\r\n\r\n* add output tokens arg to mem calc readme","shortMessageHtmlLink":"Add tied embeddings and output tokens option (#41)"}},{"before":"f5b09f60e187b5cd735e993a2150881f207193ac","after":"6c3349bf85d4603ba08934441411796f37208f16","ref":"refs/heads/qanthony/tied-embeddings","pushedAt":"2024-08-11T12:11:30.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"Quentin-Anthony","name":"Quentin Anthony","path":"/Quentin-Anthony","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/10281105?s=80&v=4"},"commit":{"message":"add output tokens arg to mem calc readme","shortMessageHtmlLink":"add output tokens arg to mem calc readme"}},{"before":"0736499d748455e0070cdbbfe9e05fc2ccd2f08c","after":"f5b09f60e187b5cd735e993a2150881f207193ac","ref":"refs/heads/qanthony/tied-embeddings","pushedAt":"2024-08-11T12:09:09.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"Quentin-Anthony","name":"Quentin Anthony","path":"/Quentin-Anthony","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/10281105?s=80&v=4"},"commit":{"message":"add output tokens to kv-mem calc","shortMessageHtmlLink":"add output tokens to kv-mem calc"}},{"before":"33a1a822e3abb771fa51ffb7171d76cd1e40b6cc","after":"86ff050b6432bb423eb20cb7770ca7dbdcef6f48","ref":"refs/heads/main","pushedAt":"2024-04-19T15:10:37.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"Quentin-Anthony","name":"Quentin Anthony","path":"/Quentin-Anthony","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/10281105?s=80&v=4"},"commit":{"message":"Add option for tied embeddings (#38)\n\n* Add tied embedding option\r\n\r\n* update readme with new tied embedding flag","shortMessageHtmlLink":"Add option for tied embeddings (#38)"}},{"before":null,"after":"0736499d748455e0070cdbbfe9e05fc2ccd2f08c","ref":"refs/heads/qanthony/tied-embeddings","pushedAt":"2024-04-19T15:09:03.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"Quentin-Anthony","name":"Quentin Anthony","path":"/Quentin-Anthony","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/10281105?s=80&v=4"},"commit":{"message":"update readme with new tied embedding flag","shortMessageHtmlLink":"update readme with new tied embedding flag"}},{"before":"69516ad419220789ac840d74d40b6610f9c58fd9","after":"8e7954fdb34ed4e73f0747a06cef51eb65615270","ref":"refs/heads/qanthony/mlp_linears","pushedAt":"2024-04-06T15:32:45.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"Quentin-Anthony","name":"Quentin Anthony","path":"/Quentin-Anthony","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/10281105?s=80&v=4"},"commit":{"message":"add linears per mlp and expansion factor args to flop calculation","shortMessageHtmlLink":"add linears per mlp and expansion factor args to flop calculation"}},{"before":null,"after":"69516ad419220789ac840d74d40b6610f9c58fd9","ref":"refs/heads/qanthony/mlp_linears","pushedAt":"2024-04-06T15:03:15.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"Quentin-Anthony","name":"Quentin Anthony","path":"/Quentin-Anthony","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/10281105?s=80&v=4"},"commit":{"message":"Add mlp linears arg and clean up args indentation","shortMessageHtmlLink":"Add mlp linears arg and clean up args indentation"}},{"before":"90321c3f8a043d7fc6950e4d04680108c00f608a","after":"a69d4071ea5d200a24325762a39683cbbe274087","ref":"refs/heads/ffn-expansion","pushedAt":"2024-03-25T23:35:35.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"haileyschoelkopf","name":"Hailey Schoelkopf","path":"/haileyschoelkopf","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/65563625?s=80&v=4"},"commit":{"message":"Update calc_transformer_flops.py","shortMessageHtmlLink":"Update calc_transformer_flops.py"}},{"before":"742ec09415f7d97649898389137e046f7e8e0649","after":"90321c3f8a043d7fc6950e4d04680108c00f608a","ref":"refs/heads/ffn-expansion","pushedAt":"2024-03-25T23:33:05.000Z","pushType":"push","commitsCount":14,"pusher":{"login":"haileyschoelkopf","name":"Hailey Schoelkopf","path":"/haileyschoelkopf","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/65563625?s=80&v=4"},"commit":{"message":"Merge branch 'main' into ffn-expansion","shortMessageHtmlLink":"Merge branch 'main' into ffn-expansion"}},{"before":null,"after":"742ec09415f7d97649898389137e046f7e8e0649","ref":"refs/heads/ffn-expansion","pushedAt":"2024-03-25T23:30:44.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"haileyschoelkopf","name":"Hailey Schoelkopf","path":"/haileyschoelkopf","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/65563625?s=80&v=4"},"commit":{"message":"add ffn-expansion-factor to flops script","shortMessageHtmlLink":"add ffn-expansion-factor to flops script"}},{"before":null,"after":"c3a308cefe951e394a38d2c9d838c5f2aed06d86","ref":"refs/heads/ffn-expansion-flops","pushedAt":"2024-03-25T23:29:11.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"haileyschoelkopf","name":"Hailey Schoelkopf","path":"/haileyschoelkopf","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/65563625?s=80&v=4"},"commit":{"message":"add ffn-expansion-factor to flops script","shortMessageHtmlLink":"add ffn-expansion-factor to flops script"}},{"before":"358af49a4ee923a055a3489d3e0e90ff6b509c1a","after":null,"ref":"refs/heads/stas00-patch-1","pushedAt":"2024-03-07T22:05:45.000Z","pushType":"branch_deletion","commitsCount":0,"pusher":{"login":"stas00","name":"Stas Bekman","path":"/stas00","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/10676103?s=80&v=4"}},{"before":"99ecff63e573748d228361f4a7416f307842eead","after":"33a1a822e3abb771fa51ffb7171d76cd1e40b6cc","ref":"refs/heads/main","pushedAt":"2024-03-07T22:04:08.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"Quentin-Anthony","name":"Quentin Anthony","path":"/Quentin-Anthony","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/10281105?s=80&v=4"},"commit":{"message":"benchmark header: add gpu info (#34)","shortMessageHtmlLink":"benchmark header: add gpu info (#34)"}},{"before":null,"after":"358af49a4ee923a055a3489d3e0e90ff6b509c1a","ref":"refs/heads/stas00-patch-1","pushedAt":"2024-03-07T17:34:16.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"stas00","name":"Stas Bekman","path":"/stas00","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/10676103?s=80&v=4"},"commit":{"message":"benchmark header: add gpu info","shortMessageHtmlLink":"benchmark header: add gpu info"}},{"before":"9153193ff0fb62716d7a2cc0b6816487bcf695e8","after":null,"ref":"refs/heads/stas00-patch-1","pushedAt":"2024-03-07T05:46:05.000Z","pushType":"branch_deletion","commitsCount":0,"pusher":{"login":"stas00","name":"Stas Bekman","path":"/stas00","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/10676103?s=80&v=4"}},{"before":"233f003388fd74d9bde65d1e4bf60ea20838de80","after":"99ecff63e573748d228361f4a7416f307842eead","ref":"refs/heads/main","pushedAt":"2024-03-07T05:39:12.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"Quentin-Anthony","name":"Quentin Anthony","path":"/Quentin-Anthony","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/10281105?s=80&v=4"},"commit":{"message":"Update transformer_flops.py (#33)","shortMessageHtmlLink":"Update transformer_flops.py (#33)"}},{"before":null,"after":"9153193ff0fb62716d7a2cc0b6816487bcf695e8","ref":"refs/heads/stas00-patch-1","pushedAt":"2024-03-07T05:36:55.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"stas00","name":"Stas Bekman","path":"/stas00","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/10676103?s=80&v=4"},"commit":{"message":"Update transformer_flops.py","shortMessageHtmlLink":"Update transformer_flops.py"}},{"before":"9d1f50df5c0f81c1dbd71bca62afe52427b07c56","after":null,"ref":"refs/heads/stas00-patch-1","pushedAt":"2024-03-07T05:24:13.000Z","pushType":"branch_deletion","commitsCount":0,"pusher":{"login":"stas00","name":"Stas Bekman","path":"/stas00","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/10676103?s=80&v=4"}},{"before":"56aeee16b246c53f5d17b76f5fc37687b13e82a9","after":"233f003388fd74d9bde65d1e4bf60ea20838de80","ref":"refs/heads/main","pushedAt":"2024-03-07T05:24:08.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"Quentin-Anthony","name":"Quentin Anthony","path":"/Quentin-Anthony","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/10281105?s=80&v=4"},"commit":{"message":"use the best experiment for max tflops (#32)","shortMessageHtmlLink":"use the best experiment for max tflops (#32)"}}],"hasNextPage":true,"hasPreviousPage":false,"activityType":"all","actor":null,"timePeriod":"all","sort":"DESC","perPage":30,"cursor":"djE6ks8AAAAEnj9_nAA","startCursor":null,"endCursor":null}},"title":"Activity ยท EleutherAI/cookbook"}