kyy/llm_trainer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Commit Graph

  • 483cdd9b6a fix README -.- 2024-06-08 23:51:56 +08:00
  • b61d25cd70 add pr ci hiyouga 2024-06-08 21:25:35 +08:00
  • 25c635ef28 Update tests.yml hiyouga 2024-06-08 21:15:36 +08:00
  • 4c4f950f39 update git workflows hiyouga 2024-06-08 21:11:32 +08:00
  • 972ec9c668 fix llamafactory-cli env hiyouga 2024-06-08 07:15:45 +08:00
  • 3ac11e77cc set dev version hiyouga 2024-06-08 06:46:09 +08:00
  • 5aa4ce4756 release v0.8.0 hiyouga 2024-06-08 05:20:54 +08:00
  • 12d79f89c5 add ultrafeedback and fineweb #4085 #4132 hiyouga 2024-06-08 02:42:34 +08:00
  • 42d9b26fc8 fix ci hiyouga 2024-06-08 02:00:44 +08:00
  • 7f20e4722a fix ci hiyouga 2024-06-08 01:57:36 +08:00
  • aa2578bea0 add ci hiyouga 2024-06-08 01:48:30 +08:00
  • 1c7f0ab519 init unittest hiyouga 2024-06-08 01:35:58 +08:00
  • 4b55f35662 Delete .readthedocs.yaml hiyouga 2024-06-08 00:58:10 +08:00
  • 54cd743ebf reorganize adapter code hiyouga 2024-06-08 00:47:23 +08:00
  • cfd62283a9 fix #4139 hoshi-hiyouga 2024-06-08 00:45:02 +08:00
  • 06e5d136a4 add resume args in webui hiyouga 2024-06-08 00:22:16 +08:00
  • 8bf9da659c fix #4137 hiyouga 2024-06-07 19:16:06 +08:00
  • cce0fad91c Update wechat.jpg hiyouga 2024-06-07 19:04:16 +08:00
  • f8d8690bf4 tiny fix hiyouga 2024-06-07 05:19:21 +08:00
  • 4489d73ac7 fix ppo trainer save zero3 model hiyouga 2024-06-07 05:14:19 +08:00
  • 2702d7e952 fix ppo in trl 0.8.6 hiyouga 2024-06-07 04:48:29 +08:00
  • f9e818d79c fix #4120 hiyouga 2024-06-07 04:18:05 +08:00
  • ccc8b64cc2 update data processors hiyouga 2024-06-07 04:15:40 +08:00
  • 181dbb0d05 Merge pull request #4009 from AlongWY/main hoshi-hiyouga 2024-06-07 03:48:46 +08:00
  • c09ad8bab3 Update supervised.py hoshi-hiyouga 2024-06-07 03:42:08 +08:00
  • 788e8232fc Update supervised.py hoshi-hiyouga 2024-06-07 03:38:23 +08:00
  • 8cecade708 Update supervised.py hoshi-hiyouga 2024-06-07 03:38:04 +08:00
  • 8e95648850 add qwen2 models hiyouga 2024-06-07 00:22:57 +08:00
  • 74f96efef9 rename files hiyouga 2024-06-07 00:09:06 +08:00
  • 45d8be8f93 add DISABLE_TORCHRUN option hiyouga 2024-06-06 23:44:58 +08:00
  • 55c18c49b0 Merge pull request #4082 from MengqingCao/bugfix hoshi-hiyouga 2024-06-06 23:38:40 +08:00
  • 751dd77bc0 Update cli.py hoshi-hiyouga 2024-06-06 23:38:09 +08:00
  • 76c61905b2 fix ppo+zero3 #3108 hiyouga 2024-06-06 23:30:07 +08:00
  • 451b6693c0 fix torch gc hiyouga 2024-06-06 20:30:25 +08:00
  • 149610c636 fix ppo dataset bug #4012 hiyouga 2024-06-06 19:03:20 +08:00
  • fad2591e31 update trainers hiyouga 2024-06-06 18:45:49 +08:00
  • 67aa78cde0 fix base64 image read #4061 hiyouga 2024-06-06 17:29:19 +08:00
  • 53eb2de75e update readme hiyouga 2024-06-06 16:59:18 +08:00
  • 87a7822b98 update readme hiyouga 2024-06-06 16:25:42 +08:00
  • cae4737907 lora modules: all by default hiyouga 2024-06-06 03:53:28 +08:00
  • c23cc63d3d add codestral 22B hiyouga 2024-06-06 03:42:50 +08:00
  • 7daf8366db lint hiyouga 2024-06-06 03:33:44 +08:00
  • f2580ad403 Merge pull request #4066 from injet-zhou/main hoshi-hiyouga 2024-06-06 03:32:04 +08:00
  • ca459f67eb Merge pull request #4080 from MengqingCao/npu hoshi-hiyouga 2024-06-06 03:15:44 +08:00
  • feaee36c46 Update export.py hoshi-hiyouga 2024-06-06 03:14:46 +08:00
  • af2c3cbee4 Update model_args.py hoshi-hiyouga 2024-06-06 03:14:23 +08:00
  • 0e740aa463 Merge pull request #4053 from hzhaoy/feature/add_select_config_file hoshi-hiyouga 2024-06-06 03:06:03 +08:00
  • 8fcc79e1e6 add vllm_dtype arg #3387 #3717 hiyouga 2024-06-06 02:53:27 +08:00
  • a12a506c3d support train from scratch #4033 #4075 hiyouga 2024-06-06 02:43:19 +08:00
  • 946f601136 support image input in api #3971 #4061 hiyouga 2024-06-06 02:29:55 +08:00
  • dc4a00dd63 update train hparams hiyouga 2024-06-06 01:49:20 +08:00
  • 4dc0632145 fix setup hiyouga 2024-06-06 01:39:02 +08:00
  • d4908d5708 add llamafactory-cli env hiyouga 2024-06-06 01:28:14 +08:00
  • 67fe822324 fix #4090 hiyouga 2024-06-06 00:50:32 +08:00
  • 2c03052662 modify export_device option MengqingCao 2024-06-05 09:37:36 +00:00
  • 83a005e3d4 fix #4079 hiyouga 2024-06-05 16:56:54 +08:00
  • eef1e542a9 update readme hiyouga 2024-06-05 16:32:32 +08:00
  • 90ed3cae92 fix #4077 MengqingCao 2024-06-05 08:03:30 +00:00
  • f48f5e646e support glm-4 hiyouga 2024-06-05 15:16:38 +08:00
  • 07045c876a add npu for model export MengqingCao 2024-06-05 07:06:40 +00:00
  • b2f0459542 add throughput entry to log faddddeout 2024-06-04 11:04:29 +00:00
  • 82a565362c update wechat hiyouga 2024-06-04 15:52:56 +08:00
  • b27c4cfcb3 add: support selecting saved configuration files and loading training parameters hzhaoy 2024-06-04 10:33:43 +08:00
  • 5a13b3baa6 tiny fix hiyouga 2024-06-04 00:31:10 +08:00
  • 91611d68c4 fix #3873 hiyouga 2024-06-04 00:21:50 +08:00
  • a18acf2abe fix #3992 hiyouga 2024-06-04 00:17:36 +08:00
  • 2187518762 fix abort in webui DDP mode hiyouga 2024-06-04 00:10:24 +08:00
  • ae18e1e251 Merge pull request #3987 from injet-zhou/main hoshi-hiyouga 2024-06-04 00:04:07 +08:00
  • 79784ebeb6 fix #4043 hiyouga 2024-06-03 23:30:37 +08:00
  • f9a206509e remove gc warnings in DPO&KTO hiyouga 2024-06-03 22:53:54 +08:00
  • 30a538e2db Merge pull request #4045 from enji-zhou/feature/add_kto hoshi-hiyouga 2024-06-03 22:09:25 +08:00
  • 24499f40dc Update trainer.py hoshi-hiyouga 2024-06-03 22:08:38 +08:00
  • 34a2c5087a fix KTO Trainer Sampler enji.zhou 2024-06-03 21:32:38 +08:00
  • 0f01500b68 Merge pull request #4006 from Uminosachi/scheduler-kwargs hoshi-hiyouga 2024-06-03 19:27:53 +08:00
  • 88681d3357 update placeholder in issue template hiyouga 2024-06-03 19:24:10 +08:00
  • d359dd2de4 Merge pull request #4011 from statelesshz/issue-template hoshi-hiyouga 2024-06-03 19:20:43 +08:00
  • eed33862bc fix #4005 #4013 hiyouga 2024-06-03 19:12:29 +08:00
  • 1539c72b94 Merge pull request #4007 from xu-song/patch-3 hoshi-hiyouga 2024-06-03 18:54:37 +08:00
  • 24e1c0e2ee fix #4022 hiyouga 2024-06-03 18:38:36 +08:00
  • 876bc92865 bump versions hiyouga 2024-06-03 18:29:38 +08:00
  • 49b1e88e3d fix data loader hint hiyouga 2024-06-03 18:28:27 +08:00
  • b47e317447 remove empty line ylfeng 2024-05-31 21:43:08 +08:00
  • 84aee57901 fix eos ylfeng 2024-05-31 21:40:41 +08:00
  • f9db439cb7 supervised packing with greedy knapsack algorithm ylfeng 2024-05-31 15:33:54 +08:00
  • dade2f083d Update model_args.py Xu Song 2024-05-31 14:35:48 +08:00
  • f78e21f341 Update bug-report.yml statelesshz 2024-05-31 13:18:18 +08:00
  • 14e97dc119 Set scheduler_specific_kwargs to get_scheduler Uminosachi 2024-05-31 13:45:39 +09:00
  • c4f50865ad update readme hiyouga 2024-05-30 16:40:17 +08:00
  • b13d03946e fix cann't interrupt training when using multi GPUs in webui faddddeout 2024-05-30 08:39:21 +00:00
  • 2f38c1f5fd Update wechat.jpg hoshi-hiyouga 2024-05-30 12:48:47 +08:00
  • 3404e8f302 fix #3837 hiyouga 2024-05-30 00:52:26 +08:00
  • 483eb47e5d Merge pull request #3829 from seanzhang-zhichen/add_dataset_sample_num hoshi-hiyouga 2024-05-30 00:25:45 +08:00
  • ca5dd7c6c1 Update loader.py hoshi-hiyouga 2024-05-30 00:20:20 +08:00
  • f9a88b89ca Update loader.py hoshi-hiyouga 2024-05-30 00:17:21 +08:00
  • b55fb611c5 Update loader.py hoshi-hiyouga 2024-05-30 00:12:12 +08:00
  • 51dd454337 Update parser.py hoshi-hiyouga 2024-05-30 00:05:20 +08:00
  • c8ae7e0e65 Update README_zh.md hoshi-hiyouga 2024-05-30 00:04:47 +08:00
  • 3761d7d5dd Update README.md hoshi-hiyouga 2024-05-30 00:04:26 +08:00
  • 8070871732 better llamaboard hiyouga 2024-05-29 23:55:38 +08:00
  • d0aa36b8ad fix cohere system hiyouga 2024-05-29 20:58:23 +08:00