kyy/llm_trainer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
114 Commits 1 Branch 0 Tags
a2f507c56238d7fb2670edbab52d6b275f245e27
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
hiyouga a2f507c562 support InternLM 2023-07-07 11:02:28 +08:00
hiyouga caa00d3ac2 fix rouge score 2023-07-06 14:28:34 +08:00
hiyouga 89c623e4bf update readme 2023-07-05 23:03:58 +08:00
hiyouga 4abd2485e1 fix streaming response in API 2023-07-05 22:42:31 +08:00
hiyouga e6603977f6 fix freeze tuning 2023-07-05 21:18:28 +08:00
hiyouga a2ba69183b fix bug in PPO stage 2023-07-05 19:14:10 +08:00
hiyouga 8e3540c62d fix compute dtype 2023-07-05 15:13:00 +08:00
hiyouga c136f362c1 support falcon model #72 2023-07-05 15:00:06 +08:00
hiyouga 966b5c70fc Update wechat.jpg 2023-07-05 00:22:22 +08:00
hiyouga cac87fd553 fix bleu score 2023-07-05 00:11:21 +08:00
hiyouga 395ed1cf1b set use_cache before saving model 2023-07-04 23:18:20 +08:00
hiyouga 65e9ce2cdd fix seq2seq predictions 2023-07-04 22:56:51 +08:00
hoshi-hiyougaandGitHub cb26f78923 Merge pull request #119 from codemayq/main 
add the pre-built version of bitsandbytes library for windows user
 2023-07-03 19:51:46 +08:00
hiyouga 0db9d29111 Update auto_gptq.py 2023-07-02 20:56:11 +08:00
hiyouga cf6d57fd3e add autogptq 2023-07-02 20:36:37 +08:00
hiyouga b8e1f09a2e Update wechat.jpg 2023-06-30 15:45:20 +08:00
hiyouga 92fa515e97 fix typo 2023-06-30 10:09:59 +08:00
hiyouga 021b035c1e Update README.md 2023-06-29 19:36:22 +08:00
hiyouga f14bd729a8 rename evaluate.py 2023-06-29 15:40:39 +08:00
hiyouga 23a7266272 Update evaluate.py 2023-06-29 15:40:03 +08:00
hiyouga 70592035b8 Update README.md 2023-06-29 15:37:19 +08:00
hiyouga 3154fec979 add open assistant dataset 2023-06-28 23:09:33 +08:00
hiyouga 4d0fddba21 update loading logic 2023-06-28 12:07:16 +08:00
hiyouga 0a46313cca fix loading best model 2023-06-28 01:55:12 +08:00
hiyouga 7826a8ca77 fix RM accuracy 2023-06-28 01:40:13 +08:00
hiyouga 9cb1af71f3 add star history 2023-06-27 23:56:29 +08:00
hiyouga 450910c1db tiny fix 2023-06-27 23:54:24 +08:00
hiyouga 18f87c1b25 fix initializing data arguments 2023-06-27 22:50:23 +08:00
hiyouga 2e01abfda5 support save full model, replace BOS token 2023-06-27 21:40:11 +08:00
hiyouga 1c732e2537 fix decoding in seq2seq 2023-06-27 19:33:08 +08:00
hiyouga 33f2141507 Update wechat.jpg 2023-06-27 16:41:09 +08:00
hiyouga 4f3772b342 Update evaluate.py 2023-06-26 23:41:33 +08:00
hiyouga 5a0a9daf74 Create evaluate.py 2023-06-26 23:30:18 +08:00
hoshi-hiyougaandGitHub 907e065454 Merge pull request #86 from Jingsong-Yan/main 
Update README.md with baichuan-7b-rtx3090
 2023-06-26 20:14:40 +08:00
hiyouga 993cabdd4c Merge branch 'main' of https://github.com/hiyouga/LLaMA-Efficient-Tuning 2023-06-26 18:07:09 +08:00
hiyouga 1175948029 fix generation in seq2seq.py 2023-06-26 18:07:06 +08:00
hoshi-hiyougaandGitHub 95b057f5af Merge pull request #84 from wu-yy/patch-1 
Update requirements.txt
 2023-06-26 15:39:08 +08:00
hiyouga cec9760eb8 support prefixes, loading multiple local files 2023-06-26 15:32:40 +08:00
hiyouga f030b09924 update api 2023-06-26 13:39:57 +08:00
hiyouga d21cc71750 Update wechat.jpg 2023-06-25 23:41:11 +08:00
hiyouga 0697643358 update readme 2023-06-23 00:17:05 +08:00
hiyouga 614d3a996c update API 2023-06-22 20:46:24 +08:00
hiyouga 76ecb8c222 match api with OpenAI format 2023-06-22 20:27:00 +08:00
hoshi-hiyougaandGitHub 9324940b76 Merge pull request #68 from mMrBun/main 
Compatible with OpenAI API.
 2023-06-22 15:52:34 +08:00
hiyouga ded5aa3c3d Update wechat.jpg 2023-06-19 19:46:04 +08:00
hiyouga f621f7631a add default template 2023-06-16 21:12:17 +08:00
hiyouga 334d1a6d26 add belle multiturn dataset 2023-06-16 20:01:16 +08:00
hiyouga a6c4b141cd fix freeze layers 2023-06-16 17:38:21 +08:00
hiyouga fc4d8155b3 add source prefix 2023-06-16 16:32:17 +08:00
hiyouga 0574b590ef support loading lora from hub 2023-06-16 00:02:17 +08:00
hiyouga 0cee6ad67f support baichuan model 2023-06-15 16:02:01 +08:00
hiyouga c527399424 fix bug in template vanilla 2023-06-15 14:36:55 +08:00
hiyouga 0a36658bb6 Update wechat.jpg 2023-06-15 13:48:53 +08:00
hiyouga d668f8b501 add BOS token in pre-training 2023-06-15 01:46:17 +08:00
hiyouga b6faf0207d support multiturn training like FastChat 2023-06-14 22:27:39 +08:00
hiyouga 875e8e2349 fix loading valuehead 2023-06-13 11:13:06 +08:00
hiyouga 531a3764d9 fix generating args 2023-06-13 01:33:56 +08:00
hiyouga cec6524d6b support RM metrics, add generating Args 2023-06-12 15:48:48 +08:00
hoshi-hiyougaandGitHub e3f380c1be Merge pull request #26 from BUAADreamer/main 
add code for reading from multi files in one directory
 2023-06-11 19:06:29 +08:00
hiyouga 2ba5d69c7f tiny fix 2023-06-07 16:42:31 +08:00
hiyouga 16c2860d56 tiny fix 2023-06-07 16:02:07 +08:00
hiyouga edafb97733 tiny fix 2023-06-07 12:58:14 +08:00
hiyouga 3875b19a34 add templates 2023-06-07 12:40:44 +08:00
hiyouga 17acf3a3eb add belle template 2023-06-07 12:30:11 +08:00
hiyouga ce43386080 tiny fix 2023-06-07 12:08:39 +08:00
hiyouga 909af8f496 add prompt template class 2023-06-07 11:55:25 +08:00
hiyouga 5d021d4ad5 fix inference, add prompt template 2023-06-07 10:52:35 +08:00
hiyouga 13d1f0709c recover logging 2023-06-06 21:36:37 +08:00
hiyouga 4eb17bcf6c support distributed quantized training 2023-06-06 17:39:41 +08:00
hiyouga 3d8d5ee5d5 add API demo from #1 2023-06-05 21:32:18 +08:00
hoshi-hiyougaandGitHub 06e1b120e1 Merge pull request #11 from hiyouga/api 
Api
 2023-06-05 20:58:02 +08:00
hiyouga a38d57ddd7 fix bug in web demo 2023-06-05 17:58:29 +08:00
hiyouga 56eb99106a increase max length in cli demo 2023-06-05 16:49:14 +08:00
hiyouga fe1d930816 implement stream generating 2023-06-05 16:43:44 +08:00
hiyouga 44298c1235 tiny fix 2023-06-05 15:25:22 +08:00
hiyouga 38b83533a4 tiny fix 2023-06-04 16:35:50 +08:00
hiyouga eac9921e5c tiny fix 2023-06-04 12:55:40 +08:00
hiyouga 3b9eee8cd2 support QLoRA 2023-06-04 00:08:56 +08:00
hiyouga 1bd13d7ca1 fix int8 inference 2023-06-03 23:22:05 +08:00
hiyouga 926291940d reduce repetition penalty 2023-06-03 21:57:39 +08:00
hiyouga 0f69a0c19e fix int8 inference 2023-06-03 21:17:47 +08:00
hiyouga de09ee1315 add ziya prompt template 2023-06-03 19:05:51 +08:00
hiyouga 771f454ff1 use low_cpu_mem_usage to speed up loading 2023-06-03 18:19:01 +08:00
hiyouga dca27b4412 add logits processor 2023-06-03 16:34:54 +08:00
hiyouga ed6161fa6a remove unused code 2023-06-03 00:10:54 +08:00
hiyouga 72a85ccc39 add wechat 2023-06-02 21:47:10 +08:00
hiyouga b8a034807e tiny fix 2023-06-02 19:02:25 +08:00
hiyouga e3aaef7d4a fix layer norm name in PPO 2023-06-02 17:30:01 +08:00
hiyouga bd565af370 fix #1 2023-06-02 14:25:00 +08:00
hiyouga 50d9a20f81 alter rewards data type 2023-06-02 14:19:51 +08:00
hiyouga e6126244c1 fix possibly OOM error 2023-06-01 23:54:44 +08:00
hiyouga fd709eacff fix bug at inference 2023-05-31 18:11:53 +08:00
hiyouga 38ca429228 update readme 2023-05-31 16:57:43 +08:00
hiyouga 740a5daf56 support BLOOM models 2023-05-31 16:54:06 +08:00
hoshi-hiyougaandGitHub c36620ece4 Merge pull request #1 from mMrBun/main 
Support conversation via API.
 2023-05-30 16:34:00 +08:00
hiyouga a72492e649 remove dummy code 2023-05-30 16:28:00 +08:00
hiyouga 6ccdfb4001 update readme 2023-05-29 21:54:01 +08:00
hiyouga 7698f9aa9a update readme 2023-05-29 21:53:02 +08:00
hiyouga 8ff96509fa add pre-training script 2023-05-29 21:37:22 +08:00
hiyouga c0e5df92d6 fix checkpoint loading 2023-05-29 17:43:16 +08:00