{"payload":{"feedbackUrl":"https://github.com/orgs/community/discussions/53140","repo":{"id":725205304,"defaultBranch":"main","name":"unsloth","ownerLogin":"unslothai","currentUserCanPush":false,"isFork":false,"isEmpty":false,"createdAt":"2023-11-29T16:50:09.000Z","ownerAvatar":"https://avatars.githubusercontent.com/u/150920049?v=4","public":true,"private":false,"isOrgOwned":true},"refInfo":{"name":"","listCacheKey":"v0:1726691011.0","currentOid":""},"activityList":{"items":[{"before":"8aceff3e7b7510250e88d5109ad947932b6898c2","after":"0fbbdfc091fc1a3b1c09b752794963681d10fad2","ref":"refs/heads/main","pushedAt":"2024-09-18T21:30:36.000Z","pushType":"push","commitsCount":2,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Merge branch 'nightly'","shortMessageHtmlLink":"Merge branch 'nightly'"}},{"before":"c730659de7a0a9e0520d01184d5dad2503b52285","after":"3fddfd5166d5fd160eca5ae1000e8a5c8a2dc465","ref":"refs/heads/nightly","pushedAt":"2024-09-18T21:23:25.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Update mapper.py","shortMessageHtmlLink":"Update mapper.py"}},{"before":"c730659de7a0a9e0520d01184d5dad2503b52285","after":"8aceff3e7b7510250e88d5109ad947932b6898c2","ref":"refs/heads/main","pushedAt":"2024-09-18T20:23:45.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Update README.md (#1036)","shortMessageHtmlLink":"Update README.md (#1036)"}},{"before":null,"after":"0f6f536b0aeb452796fa103a5c1e79825342e8aa","ref":"refs/heads/danielhanchen-patch-1","pushedAt":"2024-09-18T20:23:31.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Update README.md","shortMessageHtmlLink":"Update README.md"}},{"before":null,"after":"c730659de7a0a9e0520d01184d5dad2503b52285","ref":"refs/heads/nightly","pushedAt":"2024-09-18T07:59:18.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Update llama.py","shortMessageHtmlLink":"Update llama.py"}},{"before":"f1951c0f6d3e1f184af93e5d8f5eff6e7834e4b5","after":"c730659de7a0a9e0520d01184d5dad2503b52285","ref":"refs/heads/main","pushedAt":"2024-09-18T00:38:15.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Update llama.py","shortMessageHtmlLink":"Update llama.py"}},{"before":"62c989ef0ae0e9fbac714a4cb21eda76c1fe84b6","after":"f1951c0f6d3e1f184af93e5d8f5eff6e7834e4b5","ref":"refs/heads/main","pushedAt":"2024-09-17T17:50:59.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Update mapper.py","shortMessageHtmlLink":"Update mapper.py"}},{"before":"572c925fa7ea80b23776d8a5f94e49f8cd927664","after":"62c989ef0ae0e9fbac714a4cb21eda76c1fe84b6","ref":"refs/heads/main","pushedAt":"2024-09-16T04:50:03.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Update mapper.py","shortMessageHtmlLink":"Update mapper.py"}},{"before":"575c1bd67d973d2d1d3010a782b7d4d2cc101b8b","after":"572c925fa7ea80b23776d8a5f94e49f8cd927664","ref":"refs/heads/main","pushedAt":"2024-09-16T01:04:21.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Update _utils.py","shortMessageHtmlLink":"Update _utils.py"}},{"before":"f6458bd388089f52ae0ffb3f7ccaa5060945ccb5","after":null,"ref":"refs/heads/nightly","pushedAt":"2024-09-16T00:58:14.000Z","pushType":"branch_deletion","commitsCount":0,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"}},{"before":"e94471b8be585c703124a9a68201adffc29746aa","after":"f6458bd388089f52ae0ffb3f7ccaa5060945ccb5","ref":"refs/heads/nightly","pushedAt":"2024-09-16T00:52:35.000Z","pushType":"push","commitsCount":2,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Merge branch 'main' into nightly","shortMessageHtmlLink":"Merge branch 'main' into nightly"}},{"before":"525e878f6c3ef78d75cd2c36fdd07de0953d81d4","after":null,"ref":"refs/heads/danielhanchen-patch-1","pushedAt":"2024-09-16T00:43:14.000Z","pushType":"branch_deletion","commitsCount":0,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"}},{"before":"6c534341bb229b136f9504443f0161645d2070c5","after":"575c1bd67d973d2d1d3010a782b7d4d2cc101b8b","ref":"refs/heads/main","pushedAt":"2024-09-16T00:42:09.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Update README.md (#1033)","shortMessageHtmlLink":"Update README.md (#1033)"}},{"before":null,"after":"525e878f6c3ef78d75cd2c36fdd07de0953d81d4","ref":"refs/heads/danielhanchen-patch-1","pushedAt":"2024-09-16T00:41:57.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Update README.md","shortMessageHtmlLink":"Update README.md"}},{"before":"c6f9b2098df5792e80764c9fa59a4a85daf666b8","after":"e94471b8be585c703124a9a68201adffc29746aa","ref":"refs/heads/nightly","pushedAt":"2024-09-16T00:27:47.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Update _utils.py","shortMessageHtmlLink":"Update _utils.py"}},{"before":"737b1074891e96accc9cdae7b395c95c9320dbfc","after":"c6f9b2098df5792e80764c9fa59a4a85daf666b8","ref":"refs/heads/nightly","pushedAt":"2024-09-16T00:21:07.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Update pyproject.toml","shortMessageHtmlLink":"Update pyproject.toml"}},{"before":"e76acf8a25c9c5842d89dd77660b1fe8a57f0b43","after":"737b1074891e96accc9cdae7b395c95c9320dbfc","ref":"refs/heads/nightly","pushedAt":"2024-09-16T00:12:43.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Update pyproject.toml","shortMessageHtmlLink":"Update pyproject.toml"}},{"before":"d7f43635c0e9f9976a54c71c60813aab5e2b63c6","after":"e76acf8a25c9c5842d89dd77660b1fe8a57f0b43","ref":"refs/heads/nightly","pushedAt":"2024-09-16T00:11:53.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Update pyproject.toml","shortMessageHtmlLink":"Update pyproject.toml"}},{"before":"9c5d6c881efb906cb78892c0c6590125937b65e4","after":"d7f43635c0e9f9976a54c71c60813aab5e2b63c6","ref":"refs/heads/nightly","pushedAt":"2024-09-16T00:08:11.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Update pyproject.toml","shortMessageHtmlLink":"Update pyproject.toml"}},{"before":"a03f9d943493b5e75d6ff63219024435d026a6b1","after":"9c5d6c881efb906cb78892c0c6590125937b65e4","ref":"refs/heads/nightly","pushedAt":"2024-09-16T00:07:13.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Update pyproject.toml","shortMessageHtmlLink":"Update pyproject.toml"}},{"before":"63dcded6470f8db7bc5f398cf739bcd645086bf2","after":"a03f9d943493b5e75d6ff63219024435d026a6b1","ref":"refs/heads/nightly","pushedAt":"2024-09-16T00:06:14.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Update pyproject.toml","shortMessageHtmlLink":"Update pyproject.toml"}},{"before":"561b3779b22e9895740230f800ab165bd733852e","after":"63dcded6470f8db7bc5f398cf739bcd645086bf2","ref":"refs/heads/nightly","pushedAt":"2024-09-09T02:55:52.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Update utils.py","shortMessageHtmlLink":"Update utils.py"}},{"before":"879fc88e4b43e1e3ade9c5a61e139e7e5706af7f","after":"561b3779b22e9895740230f800ab165bd733852e","ref":"refs/heads/nightly","pushedAt":"2024-09-09T02:52:58.000Z","pushType":"push","commitsCount":6,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Merge branch 'main' into nightly","shortMessageHtmlLink":"Merge branch 'main' into nightly"}},{"before":"de43b9cedc6bd807babe3d4639c8214bec381cc3","after":"6c534341bb229b136f9504443f0161645d2070c5","ref":"refs/heads/main","pushedAt":"2024-09-09T02:47:23.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Update utils.py","shortMessageHtmlLink":"Update utils.py"}},{"before":"7476d4b5f68bb11f9f7841df4c08baf7a9e8f632","after":"de43b9cedc6bd807babe3d4639c8214bec381cc3","ref":"refs/heads/main","pushedAt":"2024-09-08T22:51:29.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Update __init__.py","shortMessageHtmlLink":"Update __init__.py"}},{"before":"d674f1c852035ed118f05a0d7c0e7e57625835c8","after":"7476d4b5f68bb11f9f7841df4c08baf7a9e8f632","ref":"refs/heads/main","pushedAt":"2024-09-08T21:30:56.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Update README.md","shortMessageHtmlLink":"Update README.md"}},{"before":"f549a5473c101bfcf279d28aa23152038b96fd22","after":"d674f1c852035ed118f05a0d7c0e7e57625835c8","ref":"refs/heads/main","pushedAt":"2024-09-08T19:29:33.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Update README.md","shortMessageHtmlLink":"Update README.md"}},{"before":"d91d40a7b6b556f2d1fdd3e1e430f7a76a799627","after":"f549a5473c101bfcf279d28aa23152038b96fd22","ref":"refs/heads/main","pushedAt":"2024-09-08T10:16:10.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Bug fixes (#1004)\n\n* Update _utils.py\r\n\r\n* Update _utils.py\r\n\r\n* Update _utils.py\r\n\r\n* Update _utils.py\r\n\r\n* Update _utils.py\r\n\r\n* Update tokenizer_utils.py\r\n\r\n* Update tokenizer_utils.py\r\n\r\n* Update tokenizer_utils.py\r\n\r\n* update token retrieval logic (#952)\r\n\r\n* Fix DPO (#947)\r\n\r\n* Update _utils.py\r\n\r\n* Update _utils.py\r\n\r\n* Update _utils.py\r\n\r\n* Update _utils.py\r\n\r\n* Update _utils.py\r\n\r\n* Update tokenizer_utils.py\r\n\r\n* Update tokenizer_utils.py\r\n\r\n* Update tokenizer_utils.py\r\n\r\n* update hf token retrieval logic\r\n\r\n---------\r\n\r\nCo-authored-by: Daniel Han \r\n\r\n* Update llama.py\r\n\r\n* get_token\r\n\r\n* Update README.md\r\n\r\n* Update gemma2.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* synchronize\r\n\r\n* Update gemma2.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* layernorm\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update gemma2.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* revert\r\n\r\n* Gemma\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update rms_layernorm.py\r\n\r\n* Update gemma2.py\r\n\r\n* Change UnslothTrainingArguments base class to SFTConfig (#979)\r\n\r\n* Cohere\r\n\r\n* Update trainer.py\r\n\r\n* Cohere\r\n\r\n* Cohere\r\n\r\n* New models\r\n\r\n* Update llama.py\r\n\r\n* Update llama.py\r\n\r\n* Update cohere.py\r\n\r\n* Update llama.py\r\n\r\n* Update cohere.py\r\n\r\n* retry\r\n\r\n* Update fast_lora.py\r\n\r\n* Update llama.py\r\n\r\n* Update fast_lora.py\r\n\r\n* Update llama.py\r\n\r\n* Update llama.py\r\n\r\n* Update cross_entropy_loss.py\r\n\r\n* _apply_lora_mlp\r\n\r\n* Update _utils.py\r\n\r\n* Gemma fixes\r\n\r\n* Update llama.py\r\n\r\n* Update flex_attention.py\r\n\r\n* Update llama.py\r\n\r\n* layernorm\r\n\r\n* Update llama.py\r\n\r\n* Update llama.py\r\n\r\n* Flex Attention\r\n\r\n* Update gemma2.py\r\n\r\n* Update __init__.py\r\n\r\n* Update flex_attention.py\r\n\r\n* Update flex_attention.py\r\n\r\n* Update flex_attention.py\r\n\r\n* Update flex_attention.py\r\n\r\n* Update flex_attention.py\r\n\r\n* Update flex_attention.py\r\n\r\n* Update flex_attention.py\r\n\r\n* Update flex_attention.py\r\n\r\n* Update flex_attention.py\r\n\r\n* Update flex_attention.py\r\n\r\n* Update flex_attention.py\r\n\r\n* Update flex_attention.py\r\n\r\n* Update flex_attention.py\r\n\r\n* Update flex_attention.py\r\n\r\n* Update flex_attention.py\r\n\r\n* Update flex_attention.py\r\n\r\n* Update flex_attention.py\r\n\r\n* Update chat_templates.py (#999)\r\n\r\nfix all misspelled \"unsued\" to \"unused\"\r\n\r\n* Update key from \"from\" to \"user\" (#1000)\r\n\r\nWhen use [tokenizer.apply_chat_template](https://huggingface.co/docs/transformers/main/en/chat_templating), the key should be \"role\" rather than \"from\", this is liknk to [this issue](https://github.com/unslothai/unsloth/issues/994)\r\n\r\nI don't know it is suitable for all situation, I also can add a dedicated parameter of the key if you think it is better.\r\n\r\n* Update chat_templates.py\r\n\r\n* Also patch the KTO trainer (#1001)\r\n\r\n* flex attention\r\n\r\n* Update llama.py\r\n\r\n* Update flex_attention.py\r\n\r\n* Update flex_attention.py\r\n\r\n* Update _utils.py\r\n\r\n* Update _utils.py\r\n\r\n* Update flex_attention.py\r\n\r\n* Update gemma2.py\r\n\r\n* Update gemma2.py\r\n\r\n---------\r\n\r\nCo-authored-by: Hafedh <70411813+not-lain@users.noreply.github.com>\r\nCo-authored-by: Tuan Pham <82665400+vTuanpham@users.noreply.github.com>\r\nCo-authored-by: Yihao Wang <42559837+AgainstEntropy@users.noreply.github.com>\r\nCo-authored-by: Peng \r\nCo-authored-by: Kyle Corbitt ","shortMessageHtmlLink":"Bug fixes (#1004)"}},{"before":"6e9d3de33011f1b8f1074329364291e6fe5ef41f","after":"879fc88e4b43e1e3ade9c5a61e139e7e5706af7f","ref":"refs/heads/nightly","pushedAt":"2024-09-08T10:15:37.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Update gemma2.py","shortMessageHtmlLink":"Update gemma2.py"}},{"before":"4e1a50c4f19673ef23a2d1059980517f19f6d7b5","after":"6e9d3de33011f1b8f1074329364291e6fe5ef41f","ref":"refs/heads/nightly","pushedAt":"2024-09-08T00:48:29.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"danielhanchen","name":"Daniel Han","path":"/danielhanchen","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/23090290?s=80&v=4"},"commit":{"message":"Update gemma2.py","shortMessageHtmlLink":"Update gemma2.py"}}],"hasNextPage":true,"hasPreviousPage":false,"activityType":"all","actor":null,"timePeriod":"all","sort":"DESC","perPage":30,"cursor":"djE6ks8AAAAEui5hDgA","startCursor":null,"endCursor":null}},"title":"Activity ยท unslothai/unsloth"}