kyy/llm_trainer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
791 Commits 1 Branch 0 Tags
b6ec112bebcb379caa32617a135df4d5d3cf865b
Commit Graph
487 Commits
Author SHA1 Message Date
hoshi-hiyougaandGitHub 6382efec52 Merge branch 'main' into feat/support_ms 2023-12-12 17:55:32 +08:00
hiyouga e6ddebd3ae fix webui 2023-12-12 15:27:40 +08:00
xingjun.wang adc98c86da add use_streaming 2023-12-12 14:23:05 +08:00
xingjun.wang 1909f0d117 fix cache dir 2023-12-12 14:21:33 +08:00
xingjun.wang 168321a4da add print info for test 2023-12-12 14:14:40 +08:00
xingjun.wang edc82b923a update cache dir 2023-12-12 13:08:18 +08:00
xingjun.wang 09533e95ed update args for MsDataset.load 2023-12-12 13:02:54 +08:00
xingjun.wang cfba1009d0 update 2023-12-12 12:03:23 +08:00
xingjun.wang 5b979147f0 for test 2023-12-12 11:52:59 +08:00
xingjun.wang 8a908a8c64 for test 2023-12-12 11:47:59 +08:00
hiyouga 8cace77808 update readme 2023-12-12 11:44:30 +08:00
hiyouga 96380f5e18 support mixtral 2023-12-12 11:39:04 +08:00
hiyouga f4657de7d5 fix baichuan resize 2023-12-11 20:55:50 +08:00
hiyouga 0239d29fa0 tiny fix 2023-12-11 18:09:40 +08:00
hiyouga 64744dde89 support resize embeddings #1786 2023-12-11 17:50:02 +08:00
hiyouga 9ce1b0e2f2 use peft 0.7.0, fix #1561 #1764 2023-12-11 17:13:40 +08:00
hiyouga 28d5de7e78 fix #1784 2023-12-09 20:53:18 +08:00
yuze.zyz 9c2247d700 support ms dataset 2023-12-08 18:00:57 +08:00
hiyouga d42c0b1d34 fix #1771 and temporarily fix #1764 2023-12-08 16:26:20 +08:00
hiyouga e25f7bae16 add models 2023-12-06 13:33:18 +08:00
hiyouga d3dccd0693 fix ppo trainer save logic 2023-12-04 19:00:19 +08:00
hiyouga c9b166615c fix #1715 2023-12-03 22:35:47 +08:00
hiyouga 438dea679b release v0.3.3 2023-12-03 21:59:45 +08:00
hiyouga 8b681ee273 fix bug 2023-12-03 21:40:40 +08:00
hiyouga 747db40172 ppo support rm server 2023-12-03 21:38:51 +08:00
hiyouga 7df4f3ab20 implement rm server #1543 2023-12-03 20:52:54 +08:00
hiyouga 03d05991f8 fix #1707 #1710 2023-12-03 11:33:12 +08:00
hiyouga b69763ff92 fix #1642 2023-12-02 00:37:53 +08:00
hiyouga 6e7af11b98 add xuanyuan models 2023-12-02 00:35:29 +08:00
hiyouga f57445c7a0 fix gptq training 2023-12-02 00:27:15 +08:00
hiyouga a973ce6e89 tiny fix 2023-12-01 23:37:10 +08:00
hiyouga 01e6c539b0 fix gptq model inference 2023-12-01 23:34:14 +08:00
hiyouga 662d9a3a4e fix #1703 2023-12-01 22:55:41 +08:00
hiyouga bd42c229b0 patch modelscope 2023-12-01 22:53:15 +08:00
hoshi-hiyougaandGitHub 00f5c9ee16 Merge branch 'main' into feat/support_ms 2023-12-01 20:23:46 +08:00
yuze.zyz 5a2392f105 remove useless code 2023-12-01 17:28:23 +08:00
tastelikefeet d9e52957e2 fix bug 2023-12-01 17:27:00 +08:00
hiyouga a5a248d569 fix err hint 2023-12-01 17:13:22 +08:00
hiyouga a51b8ec620 add err hint 2023-12-01 17:04:37 +08:00
yuze.zyz 5aa6751e52 add readme 2023-12-01 16:11:30 +08:00
hiyouga e597d3c084 tiny fix 2023-12-01 15:58:50 +08:00
hoshi-hiyougaandGitHub fbc6220692 Merge pull request #1695 from Samge0/dev 
Improve："CUDA_VISIBLE_DEVICES" read from the env
 2023-12-01 15:56:18 +08:00
hoshi-hiyougaandGitHub d043a4e7ba Merge pull request #1690 from billvsme/main 
Improve get_current_device
 2023-12-01 15:44:35 +08:00
hiyouga bf6f6aeefe fix #1696 2023-12-01 15:34:50 +08:00
tastelikefeet 8ce4d11e38 add model 2023-12-01 15:06:17 +08:00
samge 421d4de604 Improve："CUDA_VISIBLE_DEVICES" read from the env 2023-12-01 11:35:02 +08:00
billvsme 40dfcbc3d4 improve get_current_device 2023-11-30 22:40:35 +08:00
hiyouga 327d7f7efe fix #1597 2023-11-30 21:47:06 +08:00
hiyouga 1585962eb7 fix #1668 2023-11-30 21:02:00 +08:00
hiyouga a38dbf55e3 fix #1682 2023-11-30 20:03:32 +08:00