Commit Graph

  • 4a14099cfd fix #1707 #1710 hiyouga 2023-12-03 11:33:12 +08:00
  • b052574ddf add logo hiyouga 2023-12-02 01:31:24 +08:00
  • 5ea6a7c6d6 fix #1642 hiyouga 2023-12-02 00:37:53 +08:00
  • 8ca196d51f add xuanyuan models hiyouga 2023-12-02 00:35:29 +08:00
  • 5f572cbd77 fix gptq training hiyouga 2023-12-02 00:27:15 +08:00
  • 679bd3ab30 tiny fix hiyouga 2023-12-01 23:37:10 +08:00
  • da3d59fada fix gptq model inference hiyouga 2023-12-01 23:34:14 +08:00
  • 835d27151d update readme hiyouga 2023-12-01 22:58:29 +08:00
  • f1d7228a74 fix #1703 hiyouga 2023-12-01 22:55:41 +08:00
  • 72bbd5bdef patch modelscope hiyouga 2023-12-01 22:53:15 +08:00
  • ad9d866547 Merge pull request #1700 from tastelikefeet/feat/support_ms hoshi-hiyouga 2023-12-01 20:25:18 +08:00
  • a1ec668b70 Merge branch 'main' into feat/support_ms hoshi-hiyouga 2023-12-01 20:23:46 +08:00
  • 389687a56d remove useless code yuze.zyz 2023-12-01 17:28:23 +08:00
  • 97280c73b9 fix bug tastelikefeet 2023-12-01 17:27:00 +08:00
  • f3c622b665 fix err hint hiyouga 2023-12-01 17:13:22 +08:00
  • d71e8d8dbf add err hint hiyouga 2023-12-01 17:04:37 +08:00
  • 02c2089ac8 Merge pull request #1699 from Samge0/patch-1 hoshi-hiyouga 2023-12-01 16:52:57 +08:00
  • 07ad28a053 Update .gitignore SamgeShao 2023-12-01 16:37:41 +08:00
  • d323ccc3ec add readme yuze.zyz 2023-12-01 16:11:30 +08:00
  • 4738d002c7 tiny fix hiyouga 2023-12-01 15:58:50 +08:00
  • ec099b0586 Merge pull request #1695 from Samge0/dev hoshi-hiyouga 2023-12-01 15:56:18 +08:00
  • a51253fea2 Merge pull request #1690 from billvsme/main hoshi-hiyouga 2023-12-01 15:44:35 +08:00
  • 304ec9ec6a fix #1696 hiyouga 2023-12-01 15:34:50 +08:00
  • 8547085615 add model tastelikefeet 2023-12-01 15:06:17 +08:00
  • 14b139ecb5 Improve:"CUDA_VISIBLE_DEVICES" read from the env samge 2023-12-01 11:35:02 +08:00
  • 7b45f5068f improve get_current_device billvsme 2023-11-30 22:40:35 +08:00
  • 99ceee840e fix #1597 hiyouga 2023-11-30 21:47:06 +08:00
  • 8ed68301e3 fix #1668 hiyouga 2023-11-30 21:02:00 +08:00
  • 664267e050 fix #1682 hiyouga 2023-11-30 20:03:32 +08:00
  • 7ef8f46591 add models hiyouga 2023-11-30 19:16:13 +08:00
  • 6933c1fed2 fix yuze.zyz 2023-11-29 21:43:58 +08:00
  • 9d125bf533 support ms yuze.zyz 2023-11-29 20:36:55 +08:00
  • 08d5340bd8 add gpu requirement #1657 hiyouga 2023-11-29 12:05:03 +08:00
  • 0e6f4f981e fix #1658 hiyouga 2023-11-28 20:57:24 +08:00
  • 670ee3934f fix #1659 hiyouga 2023-11-28 20:52:28 +08:00
  • 569860d7ac support export size setting hiyouga 2023-11-26 18:34:09 +08:00
  • 953a562ec1 support Yi-34B-Chat models hiyouga 2023-11-23 19:31:49 +08:00
  • 7f54008d3c update readme v0.3.2 hiyouga 2023-11-21 13:15:46 +08:00
  • 5f5959bc33 set version hiyouga 2023-11-20 22:57:44 +08:00
  • 0105cd48f2 support GPTQ tuning #729 #1481 #1545 , fix chatglm template #1453 #1480 #1569 hiyouga 2023-11-20 22:52:11 +08:00
  • 28258aecd2 update ppo trainer hiyouga 2023-11-20 21:39:15 +08:00
  • e585950c54 Merge pull request #1553 from hannlp/hans hoshi-hiyouga 2023-11-20 20:32:55 +08:00
  • bcd661afa6 fix value head model resuming hiyouga 2023-11-20 19:01:37 +08:00
  • adf2730d1d fix #1567 hiyouga 2023-11-20 18:46:36 +08:00
  • ba2be6371d better data streaming hiyouga 2023-11-19 23:32:47 +08:00
  • d2ff09a404 fix model card network issue hiyouga 2023-11-19 23:03:19 +08:00
  • 9f364d3880 fix Mistral template hiyouga 2023-11-19 16:29:30 +08:00
  • cfad41b901 fix #1263 hiyouga 2023-11-19 16:05:18 +08:00
  • 6889f044fb fix #1558 hiyouga 2023-11-19 14:15:47 +08:00
  • 3d1ee27ccd fix evaluator and cached_file in 4.31.0 hiyouga 2023-11-18 19:39:23 +08:00
  • 775ce62950 update benchmark hiyouga 2023-11-18 11:30:01 +08:00
  • 821a6f2fa6 update readme hiyouga 2023-11-18 11:15:56 +08:00
  • 5197fb2fad add benchmark hiyouga 2023-11-18 11:09:52 +08:00
  • 92abe91d22 update dataset hiyouga 2023-11-17 23:19:12 +08:00
  • a7bf0b85d7 fix quantization hiyouga 2023-11-17 22:21:29 +08:00
  • 5ce5ea84a9 fix #1550 hiyouga 2023-11-17 17:23:13 +08:00
  • 992be39f90 Update README_zh.md Yuchen Han 2023-11-17 00:18:07 -08:00
  • cab80a3c56 Update README.md Yuchen Han 2023-11-17 00:17:36 -08:00
  • 6af7107938 Update workflow.py Yuchen Han 2023-11-17 00:16:27 -08:00
  • bcd31cf245 Update finetuning_args.py Yuchen Han 2023-11-17 00:15:51 -08:00
  • 85c4ccfef9 fix packages hiyouga 2023-11-17 16:11:48 +08:00
  • dc0f81aabc Merge #1544 from Outsider565/main, fix #1548 hoshi-hiyouga 2023-11-17 16:09:42 +08:00
  • 07f934566a Fix: Change rouge-chinese package name to rouge_chinese Shaowen Wang 2023-11-16 20:12:35 -06:00
  • 77cb18e9e3 fix chatglm template hiyouga 2023-11-16 22:54:15 +08:00
  • fccaecf730 Update bug-report.yml hiyouga 2023-11-16 19:37:35 +08:00
  • 53cdfe8f73 add issue template hiyouga 2023-11-16 19:35:30 +08:00
  • ea03523c6a Update issue templates hoshi-hiyouga 2023-11-16 18:56:30 +08:00
  • caf3cbf8d7 fix web ui demo hiyouga 2023-11-16 18:41:55 +08:00
  • da411066c9 fix web ui demo hiyouga 2023-11-16 17:12:23 +08:00
  • 95d0f77fc2 release v0.3.0 v0.3.0 hiyouga 2023-11-16 16:00:11 +08:00
  • 9b2654277b update readme hiyouga 2023-11-16 15:58:37 +08:00
  • f1b3bdac3f Merge #1525 from hiyouga/dev, fix #224 #336 #931 #936 #1011 hoshi-hiyouga 2023-11-16 15:47:13 +08:00
  • 595fdbd95d fix css hiyouga 2023-11-16 15:45:38 +08:00
  • dab9385297 fix bug in web ui hiyouga 2023-11-16 15:21:24 +08:00
  • df83def566 update ppo and demo in webui hiyouga 2023-11-16 14:55:26 +08:00
  • f9d4e37b3c fix bug in freeze tuning hiyouga 2023-11-16 14:25:11 +08:00
  • e59a3d71e0 tiny fix hiyouga 2023-11-16 03:27:19 +08:00
  • de3a84ac59 fix rlhf callback hiyouga 2023-11-16 03:26:19 +08:00
  • e017266b98 fix bug in PPO training hiyouga 2023-11-16 02:32:54 +08:00
  • f81a8a5e5c fix import bug hiyouga 2023-11-16 02:27:03 +08:00
  • 7a3a0144a5 support full-parameter PPO hiyouga 2023-11-16 02:08:04 +08:00
  • 8263b2d32d add demo mode for web UI hiyouga 2023-11-15 23:51:26 +08:00
  • 833cd490b8 Create CODE_OF_CONDUCT.md hoshi-hiyouga 2023-11-15 20:42:15 +08:00
  • 2162c37e41 update readme and constants hiyouga 2023-11-15 18:04:37 +08:00
  • b2ac8376e1 support multiple modules in freeze training #1514 hiyouga 2023-11-15 17:08:18 +08:00
  • 8079584143 fix imports hiyouga 2023-11-15 16:47:45 +08:00
  • 09a4474e7f disentangle model from tuner and rename modules hiyouga 2023-11-15 16:29:09 +08:00
  • 81530133ff fix #1507 hiyouga 2023-11-15 16:22:32 +08:00
  • cc4b384ac3 Update cal_lr.py hiyouga 2023-11-14 21:14:42 +08:00
  • 3852daf447 Update cal_lr.py hiyouga 2023-11-14 21:13:01 +08:00
  • 5c97111f9d Update cal_lr.py hiyouga 2023-11-14 21:09:30 +08:00
  • 75dd1f0f7e add cal_lr.py hiyouga 2023-11-14 20:58:37 +08:00
  • c9a4551012 fix #1494 hiyouga 2023-11-14 18:07:20 +08:00
  • 87197ba91d fix #1489 hiyouga 2023-11-14 15:27:05 +08:00
  • 7461bf84e5 support eval remote dataset hiyouga 2023-11-14 02:42:30 +08:00
  • fbc0357b2e fix dc link hiyouga 2023-11-13 23:22:56 +08:00
  • ec334f5891 release v0.2.2, fix #1478 #1466 v0.2.2 hiyouga 2023-11-13 23:09:05 +08:00
  • 885efe772e fix #424 hiyouga 2023-11-13 22:42:23 +08:00
  • 64fc9ba678 refactor evaluation, upgrade trl to 074 hiyouga 2023-11-13 22:20:35 +08:00
  • 989eccd286 fix flashattn warning hiyouga 2023-11-10 18:34:54 +08:00