p04798526
/
LLaMA-Factory-310P3
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Commit Graph

  • 4abd2485e1 fix streaming response in API hiyouga 2023-07-05 22:42:31 +0800
  • e6603977f6 fix freeze tuning hiyouga 2023-07-05 21:18:28 +0800
  • a2ba69183b fix bug in PPO stage hiyouga 2023-07-05 19:14:10 +0800
  • 8e3540c62d fix compute dtype hiyouga 2023-07-05 15:13:00 +0800
  • c136f362c1 support falcon model #72 hiyouga 2023-07-05 15:00:06 +0800
  • 966b5c70fc Update wechat.jpg hiyouga 2023-07-05 00:22:22 +0800
  • cac87fd553 fix bleu score hiyouga 2023-07-05 00:11:21 +0800
  • 395ed1cf1b set use_cache before saving model hiyouga 2023-07-04 23:18:20 +0800
  • 65e9ce2cdd fix seq2seq predictions hiyouga 2023-07-04 22:56:51 +0800
  • cb26f78923
         Merge pull request #119 from codemayq/main hoshi-hiyouga 2023-07-03 19:51:46 +0800
  • d3b30ecde3 add the pre-built version of bitsandbytes library for windows user codemayq 2023-07-03 13:58:10 +0800
  • 0db9d29111 Update auto_gptq.py hiyouga 2023-07-02 20:56:11 +0800
  • cf6d57fd3e add autogptq hiyouga 2023-07-02 20:36:37 +0800
  • b8e1f09a2e Update wechat.jpg hiyouga 2023-06-30 15:45:20 +0800
  • 92fa515e97 fix typo hiyouga 2023-06-30 10:09:59 +0800
  • 021b035c1e Update README.md hiyouga 2023-06-29 19:36:22 +0800
  • f14bd729a8 rename evaluate.py hiyouga 2023-06-29 15:40:39 +0800
  • 23a7266272 Update evaluate.py hiyouga 2023-06-29 15:40:03 +0800
  • 70592035b8 Update README.md hiyouga 2023-06-29 15:37:19 +0800
  • 3154fec979 add open assistant dataset hiyouga 2023-06-28 23:09:33 +0800
  • 4d0fddba21 update loading logic hiyouga 2023-06-28 12:07:16 +0800
  • 0a46313cca fix loading best model hiyouga 2023-06-28 01:55:12 +0800
  • 7826a8ca77 fix RM accuracy hiyouga 2023-06-28 01:40:13 +0800
  • 9cb1af71f3 add star history hiyouga 2023-06-27 23:56:29 +0800
  • 450910c1db tiny fix hiyouga 2023-06-27 23:54:24 +0800
  • 18f87c1b25 fix initializing data arguments hiyouga 2023-06-27 22:50:23 +0800
  • 2e01abfda5 support save full model, replace BOS token hiyouga 2023-06-27 21:40:11 +0800
  • 1c732e2537 fix decoding in seq2seq hiyouga 2023-06-27 19:33:08 +0800
  • 33f2141507 Update wechat.jpg hiyouga 2023-06-27 16:41:09 +0800
  • 4f3772b342 Update evaluate.py hiyouga 2023-06-26 23:41:33 +0800
  • 5a0a9daf74 Create evaluate.py hiyouga 2023-06-26 23:30:18 +0800
  • 907e065454
         Merge pull request #86 from Jingsong-Yan/main hoshi-hiyouga 2023-06-26 20:14:40 +0800
  • 90bb5b6f37
         Update README.md with baichuan-7b-rtx3090 Jingsong-Yan 2023-06-26 19:45:41 +0800
  • 993cabdd4c Merge branch 'main' of https://github.com/hiyouga/LLaMA-Efficient-Tuning hiyouga 2023-06-26 18:07:09 +0800
  • 1175948029 fix generation in seq2seq.py hiyouga 2023-06-26 18:07:06 +0800
  • 95b057f5af
         Merge pull request #84 from wu-yy/patch-1 hoshi-hiyouga 2023-06-26 15:39:08 +0800
  • e2a16d549e
         Update requirements.txt 蓝鲸123 2023-06-26 15:36:19 +0800
  • cec9760eb8 support prefixes, loading multiple local files hiyouga 2023-06-26 15:32:40 +0800
  • 785fdc4b3a Support baichuan-7B training on RTX3090 yixue 2023-06-26 06:33:27 +0000
  • f030b09924 update api hiyouga 2023-06-26 13:39:57 +0800
  • d21cc71750 Update wechat.jpg hiyouga 2023-06-25 23:41:11 +0800
  • 0697643358 update readme hiyouga 2023-06-23 00:17:05 +0800
  • 614d3a996c update API hiyouga 2023-06-22 20:46:24 +0800
  • 76ecb8c222 match api with OpenAI format hiyouga 2023-06-22 20:27:00 +0800
  • 9324940b76
         Merge pull request #68 from mMrBun/main hoshi-hiyouga 2023-06-22 15:52:34 +0800
  • 6e4db0903f Compatible with OpenAI API. Bun 2023-06-21 14:45:04 +0800
  • ded5aa3c3d Update wechat.jpg hiyouga 2023-06-19 19:46:04 +0800
  • 2f6c64b839
         Update README.md Ikko Eltociear Ashimine 2023-06-17 21:49:42 +0900
  • f621f7631a add default template hiyouga 2023-06-16 21:12:17 +0800
  • 334d1a6d26 add belle multiturn dataset hiyouga 2023-06-16 20:01:16 +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
  • 7e4170f2f5 add server.py to support stream generator api BUAADreamer 2023-06-14 08:59:04 +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
  • 6c46a25ff4
         add missing package 少年 2023-06-08 19:34:07 +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