Commit Graph

  • da9c1a383e 第一次提交 majiahui@haimaqingfan.com 2023-11-02 15:18:46 +0800
  • bd3126ec63 生成英文内容 majiahui@haimaqingfan.com 2023-07-30 12:43:11 +0800
  • a6c4b141cd fix freeze layers hiyouga 2023-06-16 17:38:21 +0800
  • fc4d8155b3 add source prefix hiyouga 2023-06-16 16:32:17 +0800
  • 0574b590ef support loading lora from hub hiyouga 2023-06-16 00:02:17 +0800
  • 0cee6ad67f support baichuan model hiyouga 2023-06-15 16:02:01 +0800
  • c527399424 fix bug in template vanilla hiyouga 2023-06-15 14:36:55 +0800
  • 0a36658bb6 Update wechat.jpg hiyouga 2023-06-15 13:48:53 +0800
  • d668f8b501 add BOS token in pre-training hiyouga 2023-06-15 01:46:17 +0800
  • b6faf0207d support multiturn training like FastChat hiyouga 2023-06-14 22:27:39 +0800
  • 875e8e2349 fix loading valuehead hiyouga 2023-06-13 11:13:06 +0800
  • 531a3764d9 fix generating args hiyouga 2023-06-13 01:33:56 +0800
  • cec6524d6b support RM metrics, add generating Args hiyouga 2023-06-12 15:48:48 +0800
  • e3f380c1be
    Merge pull request #26 from BUAADreamer/main hoshi-hiyouga 2023-06-11 19:06:29 +0800
  • e3b53a67c7 update json line file to .jsonl BUAADreamer 2023-06-11 18:59:19 +0800
  • 676d910260 add some BUAADreamer 2023-06-11 18:55:53 +0800
  • a2af9df5a9 add code for reading from multi files in one directory BUAADreamer 2023-06-10 16:27:30 +0800
  • 3dd5f9a874 add code for reading from multi files in one directory BUAADreamer 2023-06-10 15:53:47 +0800
  • 2ba5d69c7f tiny fix hiyouga 2023-06-07 16:42:31 +0800
  • 16c2860d56 tiny fix hiyouga 2023-06-07 16:02:07 +0800
  • edafb97733 tiny fix hiyouga 2023-06-07 12:58:14 +0800
  • 3875b19a34 add templates hiyouga 2023-06-07 12:40:44 +0800
  • 17acf3a3eb add belle template hiyouga 2023-06-07 12:30:11 +0800
  • ce43386080 tiny fix hiyouga 2023-06-07 12:08:39 +0800
  • 909af8f496 add prompt template class hiyouga 2023-06-07 11:55:25 +0800
  • 5d021d4ad5 fix inference, add prompt template hiyouga 2023-06-07 10:52:35 +0800
  • 13d1f0709c recover logging hiyouga 2023-06-06 21:36:37 +0800
  • 4eb17bcf6c support distributed quantized training hiyouga 2023-06-06 17:39:41 +0800
  • 3d8d5ee5d5 add API demo from #1 hiyouga 2023-06-05 21:32:18 +0800
  • 06e1b120e1
    Merge pull request #11 from hiyouga/api hoshi-hiyouga 2023-06-05 20:58:02 +0800
  • a38d57ddd7 fix bug in web demo hiyouga 2023-06-05 17:58:29 +0800
  • 56eb99106a increase max length in cli demo hiyouga 2023-06-05 16:49:14 +0800
  • fe1d930816 implement stream generating hiyouga 2023-06-05 16:43:44 +0800
  • 44298c1235 tiny fix hiyouga 2023-06-05 15:25:22 +0800
  • 38b83533a4 tiny fix hiyouga 2023-06-04 16:35:50 +0800
  • eac9921e5c tiny fix hiyouga 2023-06-04 12:55:40 +0800
  • 3b9eee8cd2 support QLoRA hiyouga 2023-06-04 00:08:56 +0800
  • 1bd13d7ca1 fix int8 inference hiyouga 2023-06-03 23:22:05 +0800
  • 926291940d reduce repetition penalty hiyouga 2023-06-03 21:57:39 +0800
  • 0f69a0c19e fix int8 inference hiyouga 2023-06-03 21:17:47 +0800
  • de09ee1315 add ziya prompt template hiyouga 2023-06-03 19:05:51 +0800
  • 771f454ff1 use low_cpu_mem_usage to speed up loading hiyouga 2023-06-03 18:19:01 +0800
  • dca27b4412 add logits processor hiyouga 2023-06-03 16:34:54 +0800
  • ed6161fa6a remove unused code hiyouga 2023-06-03 00:10:54 +0800
  • 72a85ccc39 add wechat hiyouga 2023-06-02 21:47:10 +0800
  • b8a034807e tiny fix hiyouga 2023-06-02 19:02:25 +0800
  • e3aaef7d4a fix layer norm name in PPO hiyouga 2023-06-02 17:30:01 +0800
  • bd565af370 fix #1 hiyouga 2023-06-02 14:25:00 +0800
  • 50d9a20f81 alter rewards data type hiyouga 2023-06-02 14:19:51 +0800
  • e6126244c1 fix possibly OOM error hiyouga 2023-06-01 23:54:44 +0800
  • fd709eacff fix bug at inference hiyouga 2023-05-31 18:11:53 +0800
  • 38ca429228 update readme hiyouga 2023-05-31 16:57:43 +0800
  • 740a5daf56 support BLOOM models hiyouga 2023-05-31 16:54:06 +0800
  • c36620ece4
    Merge pull request #1 from mMrBun/main hoshi-hiyouga 2023-05-30 16:34:00 +0800
  • a72492e649 remove dummy code hiyouga 2023-05-30 16:28:00 +0800
  • 748b804bac Support conversation via API. mMrBun 2023-05-30 15:00:28 +0800
  • e821682430 Support conversation via API. mMrBun 2023-05-30 14:46:22 +0800
  • 6ccdfb4001 update readme hiyouga 2023-05-29 21:54:01 +0800
  • 7698f9aa9a update readme hiyouga 2023-05-29 21:53:02 +0800
  • 8ff96509fa add pre-training script hiyouga 2023-05-29 21:37:22 +0800
  • c0e5df92d6 fix checkpoint loading hiyouga 2023-05-29 17:43:16 +0800
  • ce71cc8b6d tiny fix hiyouga 2023-05-29 09:42:29 +0800
  • 166c837b95 tiny fix hiyouga 2023-05-28 21:48:33 +0800
  • 0c9fda01e3 use fp16 model, add logcallback hiyouga 2023-05-28 21:30:28 +0800
  • 769c6ab56b Initial commit hiyouga 2023-05-28 18:09:04 +0800