Commit Graph

Select branches

Hide Pull Requests

main

Mono Color

• 156710a995 Update README_zh.md hiyouga 2023-08-11 14:06:02 +08:00
• d3844e97e3 add defaults hiyouga 2023-08-11 13:56:26 +08:00
• d59f938959 fix stop word in baichuan template hiyouga 2023-08-11 13:51:46 +08:00
• 9c6dd10514 fix baichuan template hiyouga 2023-08-11 13:45:47 +08:00
• 3ec4351cfd support DPO training (2305.18290) hiyouga 2023-08-11 03:02:53 +08:00
• 685dae4eff Merge pull request #451 from jovialchen/main hoshi-hiyougaandGitHub 2023-08-10 17:25:38 +08:00
• ad6e7c76c7 fix webui val size hiyouga 2023-08-10 15:20:44 +08:00
• 3e000c2b60 huggingface login for projects must login while running jiongxuc 2023-08-10 14:57:12 +08:00
• eb6e571cb7 fix template hiyouga 2023-08-09 23:14:27 +08:00
• ac29f4d5f0 fix template hiyouga 2023-08-09 23:10:20 +08:00
• d86ea314a1 support val set in streaming mode hiyouga 2023-08-09 23:00:26 +08:00
• 572ea3bafb fix tokenizer hiyouga 2023-08-09 17:52:15 +08:00
• ef5b299b18 Update wechat.jpg hiyouga 2023-08-09 17:36:17 +08:00
• 2ec68d3398 add last_checkpoint support niuba 2023-08-09 16:39:27 +08:00
• df946e6949 fix sft trainer hiyouga 2023-08-09 16:35:03 +08:00
• 39cd8b6989 fix rm #420, fix template #426, fix #423 hiyouga 2023-08-09 16:23:31 +08:00
• 2d90685358 fix llama2 template hoshi-hiyougaandGitHub 2023-08-09 00:58:27 +08:00
• 32fa5e8d70 fix tokenizer hoshi-hiyougaandGitHub 2023-08-09 00:54:54 +08:00
• 3a720aac66 update webui hiyouga 2023-08-09 00:26:11 +08:00
• eecc4b2131 fix tokenizer #417 hiyouga 2023-08-08 23:59:41 +08:00
• caa0eda27d fix bug hiyouga 2023-08-08 21:28:28 +08:00
• 4b841a6b35 fix bug hiyouga 2023-08-08 17:55:55 +08:00
• a9980617f5 fix chatml template #408 hiyouga 2023-08-08 17:44:39 +08:00
• 5453b93db0 update args spec hiyouga 2023-08-07 15:23:35 +08:00
• 20cf27976f update readme hiyouga 2023-08-07 15:02:02 +08:00
• cacd5b703d Merge branch 'main' of https://github.com/hiyouga/LLaMA-Efficient-Tuning hiyouga 2023-08-07 13:59:16 +08:00
• 081345baca fix #376 hiyouga 2023-08-07 13:58:59 +08:00
• da42d289ee Merge pull request #382 from hiyouga/feature-updateReadme hoshi-hiyougaandGitHub 2023-08-07 13:43:38 +08:00
• 220175ab24 update trainer hiyouga 2023-08-07 13:34:35 +08:00
• 293bd95712 add detailed model configs codemayq 2023-08-07 09:30:23 +08:00
• e21ae01356 fix qwen eos token hiyouga 2023-08-06 13:31:17 +08:00
• 7f18d2a335 fix qwen tokenizer #361 hiyouga 2023-08-05 17:06:05 +08:00
• 1afa51c2fa fix template for tiktoken hiyouga 2023-08-05 13:42:42 +08:00
• 53d95725c5 remove redundant code hiyouga 2023-08-05 00:27:27 +08:00
• c183b3551d fix template hiyouga 2023-08-05 00:25:00 +08:00
• e4a15f863c fix llama2 template hiyouga 2023-08-05 00:07:54 +08:00
• f30fc3b030 Support safe ChatML template, fix qwen tok #351 #354 hoshi-hiyougaandGitHub 2023-08-05 00:00:23 +08:00
• d87c8fd8ab fix bos and eos token hiyouga 2023-08-04 23:55:57 +08:00
• 8172ad1b5e fix encode hiyouga 2023-08-04 23:27:55 +08:00
• b4852f9406 support chatml safe encoding hiyouga 2023-08-04 23:14:28 +08:00
• 69744c17e8 support interleave probs hiyouga 2023-08-04 21:27:35 +08:00
• 6bdb7f0910 Update wechat.jpg hiyouga 2023-08-04 15:03:53 +08:00
• d6b14658d4 fix webui export model hiyouga 2023-08-04 14:20:27 +08:00
• a0173c427d fix mtloader hiyouga 2023-08-03 19:29:02 +08:00
• ff98f1cba8 tiny fix hiyouga 2023-08-03 17:42:28 +08:00
• 2780792754 fix qwen inference hiyouga 2023-08-03 16:31:55 +08:00
• ea30da4794 fix qwen inference hiyouga 2023-08-03 16:15:38 +08:00
• 87f8f830e2 support Qwen-7B, fix InternLM-7B inference hiyouga 2023-08-03 15:53:32 +08:00
• 53d6dc396d update web demo hiyouga 2023-08-03 13:28:28 +08:00
• e23a3a366c fix webui hiyouga 2023-08-03 12:43:12 +08:00
• 08f180e788 modify code structure hiyouga 2023-08-02 23:17:36 +08:00
• 1d8a1878ea fix PPO trainer hiyouga 2023-08-02 19:10:23 +08:00
• b5ba87952a update ppo trainer hiyouga 2023-08-02 18:46:41 +08:00
• 286f7be346 fix memory leak of PPO trainer hiyouga 2023-08-02 17:41:34 +08:00
• c689857bbb release v0.1.5 hiyouga 2023-08-02 16:10:31 +08:00
• 8ca01e53a8 Merge pull request #307 from GitYCC/feature/fix-llama2-prompt-template hoshi-hiyougaandGitHub 2023-08-02 15:51:28 +08:00
• ca125da0eb [fix] Remove useless code YC Chen 2023-08-02 14:35:35 +08:00
• 4323773089 [feature] Fix template of Llama2 to match the offical template YC Chen 2023-08-02 14:05:43 +08:00
• 968ce0dcce fix bug in preprocessing hiyouga 2023-08-02 01:10:28 +08:00
• ccde51c5ea update readme hiyouga 2023-08-01 18:48:27 +08:00
• e3f80774c4 fix #296 hiyouga 2023-08-01 18:43:53 +08:00
• e6a3894b99 Fix #294 hiyouga 2023-08-01 18:13:03 +08:00
• b9cdff41bb restore from git lfs hiyouga 2023-08-01 16:33:25 +08:00
• 7cdb720da2 Update .gitattributes hiyouga 2023-08-01 16:28:54 +08:00
• 9879cd64da Update wechat.jpg hiyouga 2023-08-01 12:27:37 +08:00
• befaab5720 fix webui hiyouga 2023-08-01 12:11:37 +08:00
• ac88ce5233 fix RM save model hiyouga 2023-08-01 11:56:17 +08:00
• 82e793ddb4 use git lfs hiyouga 2023-08-01 10:14:08 +08:00
• 973a638665 release v0.1.4 hiyouga 2023-08-01 10:08:47 +08:00
• d3a0692d4d fix inference hiyouga 2023-08-01 00:06:48 +08:00
• 9cb1f119a4 fix arg check hiyouga 2023-07-31 23:48:57 +08:00
• 62dca5bb82 update readme hiyouga 2023-07-31 23:42:32 +08:00
• 0411a4b3e1 support streaming data, fix #284 #274 #268 hiyouga 2023-07-31 23:33:00 +08:00
• 513e1f1ec9 Update data_args.py hiyouga 2023-07-28 17:42:41 +08:00
• 5ee87138e4 update readme hiyouga 2023-07-28 17:36:00 +08:00
• 91dd17d8a6 fix #268 hiyouga 2023-07-28 17:02:26 +08:00
• 553b97a9d5 Update wechat.jpg hiyouga 2023-07-27 15:09:29 +08:00
• f5c2ccdde4 update dataset hiyouga 2023-07-26 17:05:12 +08:00
• 00efa8a07f fix #242 hiyouga 2023-07-25 17:04:02 +08:00
• 2c31e05e63 update wechat hiyouga 2023-07-24 20:33:40 +08:00
• 0c05d00bfb Add files via upload hoshi-hiyougaandGitHub 2023-07-24 18:08:09 +08:00
• 182b425043 update dataset hiyouga 2023-07-23 20:01:43 +08:00
• 6a2967ff7a Update README_zh.md hiyouga 2023-07-22 14:31:16 +08:00
• 035c966d5c update readme, fix web ui postprocess hiyouga 2023-07-22 14:29:22 +08:00
• 21daf34f0c Merge pull request #221 from mrhan1993/main hoshi-hiyougaandGitHub 2023-07-22 13:04:25 +08:00
• 7007fbc0b6 Merge branch 'hiyouga:main' into main NULLandGitHub 2023-07-21 17:00:26 +08:00
• 9f0b57b370 根据GLM Efficient Tuning添加中文README，web添加了server_port mrhan1993 2023-07-21 16:57:58 +08:00
• 0b6150bc31 release v0.1.3 hiyouga 2023-07-21 16:48:34 +08:00
• d2f18197e3 fix save function hiyouga 2023-07-21 14:09:07 +08:00
• 1d1d8538c9 Update runner.py hiyouga 2023-07-21 13:35:19 +08:00
• ed0e186a13 update web UI, support rm predict #210 hiyouga 2023-07-21 13:27:27 +08:00
• 4c45a3a884 release v0.1.2 hiyouga 2023-07-20 22:33:59 +08:00
• 8333795fcb fix api hiyouga 2023-07-20 22:14:54 +08:00
• 6022adb72e Merge pull request #213 from Ehco1996/patch-1 hoshi-hiyougaandGitHub 2023-07-20 22:12:07 +08:00
• 4d1641c1bf update UI, fix #212 hiyouga 2023-07-20 22:09:06 +08:00
• b2874a72e4 feat: support pass args before init web app EhcoandGitHub 2023-07-20 21:49:26 +08:00
• c3fcb67486 Update README.md hiyouga 2023-07-20 17:23:16 +08:00
• 67a2773074 simplify code hiyouga 2023-07-20 15:08:57 +08:00
• d1d8e8bae1 tiny fix hiyouga 2023-07-19 22:53:46 +08:00
• d111e658a2 fix #199 hiyouga 2023-07-19 22:51:29 +08:00