kyy/llm_trainer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
678 Commits 1 Branch 0 Tags
87ef3f47b519677e6a7c81ff45584acb34339f3a
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
hiyouga 87ef3f47b5 update dc link 2023-12-15 22:11:31 +08:00
hoshi-hiyougaandGitHub e2bd597b3c Merge pull request #1864 from hiyouga/dev 
Refactor hyper-parameters of adapters and model loader
 2023-12-15 22:06:56 +08:00
hiyouga 00c77104f8 fix bug 2023-12-15 21:54:02 +08:00
hiyouga 9e509b99af fix bug 2023-12-15 21:49:26 +08:00
hiyouga 2740aa9cbb add configurer 2023-12-15 21:46:40 +08:00
hiyouga 0716f5e470 refactor adapter hparam 2023-12-15 20:53:11 +08:00
hiyouga d4c351f1ec add loftq 2023-12-14 21:53:56 +08:00
hiyouga bfdee1608f fix valuehead model 2023-12-14 20:15:20 +08:00
hoshi-hiyouga bf2d9c8feb Update wechat.jpg 2023-12-13 18:23:18 +08:00
hoshi-hiyouga 81167cd19d tiny fix 2023-12-13 17:32:36 +08:00
hoshi-hiyouga 9b0630f84f revert peft version 2023-12-13 10:49:45 +08:00
hoshi-hiyouga 573a12c86b update peft version 2023-12-13 10:23:51 +08:00
hoshi-hiyouga 6953096c9d tiny fix 2023-12-13 10:21:29 +08:00
hoshi-hiyouga 1fcd545c3d fix #1819 2023-12-13 10:14:01 +08:00
hiyouga 3a8a50d4d4 remove loftq 2023-12-13 01:53:46 +08:00
hiyouga 2c8e88f9c1 fix sharegpt loading 2023-12-13 00:56:16 +08:00
hiyouga 3552035d7e add model urls 2023-12-13 00:09:17 +08:00
hiyouga 28cc07868c update readme 2023-12-12 23:30:29 +08:00
hiyouga 6219dfbd93 support loftq 2023-12-12 22:47:06 +08:00
hiyouga ada0e536c9 fix #1795 2023-12-12 19:58:34 +08:00
hiyouga 0a9c6e0146 support system column #1765 2023-12-12 19:45:59 +08:00
hiyouga d5b2c57a35 fix modelscope data hub 2023-12-12 18:33:06 +08:00
hoshi-hiyougaandGitHub 382319915c Merge pull request #1802 from tastelikefeet/feat/support_ms 
Support ModelScope Datahub
 2023-12-12 17:58:37 +08:00
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
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
hiyouga d42c0b1d34 fix #1771 and temporarily fix #1764 2023-12-08 16:26:20 +08:00
hiyouga 3378337b1a Update wechat.jpg 2023-12-07 22:05:04 +08:00
hiyouga d60cf551a1 Update wechat.jpg 2023-12-06 17:10:02 +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 997b65f291 update readme 2023-12-04 11:22:01 +08:00
hiyouga 8ede3128df update readme 2023-12-04 11:02:29 +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 5b78e269b6 add logo 2023-12-02 01:31:24 +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 0cb260f453 update readme 2023-12-01 22:58:29 +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 3a64506031 Merge pull request #1700 from tastelikefeet/feat/support_ms 
Support ModelScope hub
 2023-12-01 20:25:18 +08:00
hoshi-hiyougaandGitHub 00f5c9ee16 Merge branch 'main' into feat/support_ms 2023-12-01 20:23:46 +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
hoshi-hiyougaandGitHub aec946b119 Merge pull request #1699 from Samge0/patch-1 
Update .gitignore
 2023-12-01 16:52:57 +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
hoshi-hiyougaandGitHub a0fde6e421 Merge pull request #1689 from mlinmg/patch-2 
Update dataset_info.json - Added Nectar
 2023-12-01 14:29:36 +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
hiyouga 509abe8864 add models 2023-11-30 19:16:13 +08:00
hiyouga 9d38e5687d add gpu requirement #1657 2023-11-29 12:05:03 +08:00
hiyouga 77d1b14fc2 fix #1658 2023-11-28 20:57:24 +08:00
hiyouga 475a3fa0f4 fix #1659 2023-11-28 20:52:28 +08:00
hiyouga c2d4300ac4 Update wechat.jpg 2023-11-28 17:27:23 +08:00
hiyouga 859a6ea942 support export size setting 2023-11-26 18:34:09 +08:00
hiyouga ff1c289229 support Yi-34B-Chat models 2023-11-23 19:31:49 +08:00
hiyouga 5085b00a1d update readme 2023-11-21 13:15:46 +08:00
hiyouga 35c2da3eba set version 2023-11-20 22:57:44 +08:00
hiyouga 9ea9380145 support GPTQ tuning #729 #1481 #1545 , fix chatglm template #1453 #1480 #1569 2023-11-20 22:52:11 +08:00
hiyouga 5021062493 update ppo trainer 2023-11-20 21:39:15 +08:00
hoshi-hiyougaandGitHub 48211e3799 Merge pull request #1553 from hannlp/hans 
Change the default argument settings for PPO training
 2023-11-20 20:32:55 +08:00
hiyouga 2a36fd5064 fix value head model resuming 2023-11-20 19:01:37 +08:00
hiyouga 99a3f06377 fix #1567 2023-11-20 18:46:36 +08:00
hiyouga 00baaa990e better data streaming 2023-11-19 23:32:47 +08:00
hiyouga 211b2db5a8 fix model card network issue 2023-11-19 23:03:19 +08:00
hiyouga bfb9433165 fix Mistral template 
https://github.com/lm-sys/FastChat/pull/2547
 2023-11-19 16:29:30 +08:00
hiyouga 065bfaeed4 fix #1263 2023-11-19 16:05:18 +08:00
hiyouga 1740131d63 fix #1558 2023-11-19 14:15:47 +08:00
hiyouga ff6056405d fix evaluator and cached_file in 4.31.0 2023-11-18 19:39:23 +08:00
hiyouga a2019c8b61 update benchmark 2023-11-18 11:30:01 +08:00
hiyouga 90212280d6 update readme 2023-11-18 11:15:56 +08:00
hiyouga 329134f58c add benchmark 2023-11-18 11:09:52 +08:00
hiyouga 7b1aa6f63c update dataset 2023-11-17 23:19:12 +08:00
hiyouga ccb0f58e22 fix quantization 2023-11-17 22:21:29 +08:00
hiyouga 1bbc1be95e fix #1550 2023-11-17 17:23:13 +08:00
hiyouga 999bc0ed93 fix packages 2023-11-17 16:11:48 +08:00
hoshi-hiyougaandGitHub 7f9770b2c6 Merge #1544 from Outsider565/main, fix #1548 
Fix: Change rouge-chinese package name to rouge_chinese
 2023-11-17 16:09:42 +08:00
hiyouga ed9f7705ef fix chatglm template 2023-11-16 22:54:15 +08:00
hiyouga 438c374567 Update bug-report.yml 2023-11-16 19:37:35 +08:00
hiyouga 9e0bfcfc14 add issue template 2023-11-16 19:35:30 +08:00
hoshi-hiyougaandGitHub dea176f88e Update issue templates 2023-11-16 18:56:30 +08:00
hiyouga 10ce87e088 fix web ui demo 2023-11-16 18:41:55 +08:00