24 Commits
Author SHA1 Message Date
Michael J Clark 701b3fa63b Update README.md 2024-03-01 09:14:21 +08:00
Michael J Clark ec0bce8601 Update README.md 2024-02-03 14:02:27 +08:00
deep1 7d2d9a4e8d fix the id_n thing
distinguish between _No and No
2023-05-28 19:15:13 +08:00
deep1 0f7b6459f4 4bit hf works better 2023-05-28 14:20:26 +08:00
deep1 61d1833d6d doc_reqs before upgrading to hf 4bit 2023-05-28 14:19:42 +08:00
deep1 e4d009e3d1 I want to use the hs from generate not forward 2023-05-27 20:37:00 +08:00
deep1 56cfb17bca misc 2023-05-22 07:09:05 +08:00
deep1 556e62101b the generation seems to works! 2023-05-21 17:20:18 +08:00
deep1 9dc85682c2 misc 2023-05-21 11:24:47 +08:00
deep1 45c4356a8b 13b 2023-05-20 18:08:51 +08:00
wassname 1c860bbbeb reqs 2023-05-20 10:29:17 +08:00
wassname 32e9fb9440 trying to improve and debug generation 2023-05-20 10:28:37 +08:00
wassname ead980293f misc 2023-05-19 09:19:14 +08:00
wassname 2e9055f746 lightning 2023-05-14 20:54:07 +08:00
wassname e688582b45 misc 2023-05-07 19:23:22 +08:00
wassname 961ef59d2b many shot 2023-05-07 17:24:49 +08:00
wassname 60b8a9732a add reqs 2023-05-07 15:46:44 +08:00
wassname 09aad3154f working with llama 2023-05-07 15:34:49 +08:00
Collin Burns 1c63b4c77e Create LICENSE.md 2023-02-01 11:28:36 -08:00
Collin Burns 889165b7aa Merge pull request #1 from tkukurin/tk/fix-batch
Bug fix for when using multiple batches per epoch
2023-01-23 11:40:57 -08:00
Collin Burns aaa00c9174 Fixed a bug where the sigmoid was missing for the linear probe. 2023-01-23 11:04:27 -08:00
Toni Kukurin a8cfa188b1 fix the ipynb as well 2022-12-10 14:26:54 +00:00
Toni Kukurin f00a5b84b3 train all batches! 2022-12-10 14:23:55 +00:00
Collin Burns 1fb40eefbd Initial commit 2022-12-07 10:13:14 -08:00