Commit Graph

38 Commits

Author SHA1 Message Date
Rohan Taori
761dc5bfbd
Update README.md 2023-05-29 21:36:57 -07:00
Xuechen Li
65512697dc
Merge pull request #219 from tatsu-lab/doc
patch documentation.
2023-04-16 15:18:50 -07:00
Xuechen Li
679f56d424 patch documentation. 2023-04-16 15:18:19 -07:00
Xuechen Li
e408b27bfd
Merge pull request #216 from tatsu-lab/hf-migrate
let training code run with huggingface transformers main
2023-04-15 15:50:02 -07:00
Xuechen Li
3783d185b5 migrate to latest main for hf transformers. 2023-04-15 15:48:27 -07:00
Xuechen Li
7a95b21d2c store tokenizer for recovered dir. 2023-04-15 15:47:59 -07:00
Xuechen Li
c53841268d
Merge pull request #209 from tatsu-lab/weight_diff
add weight diff conversion.
2023-04-13 10:52:25 -07:00
Xuechen Li
aeecd8c0ad add weight diff conversion. 2023-04-13 10:52:08 -07:00
Xuechen Li
aa65c492bb
Merge pull request #158 from tatsu-lab/hparams
update hyperparameters.
2023-03-29 13:08:02 -07:00
Xuechen Li
f208cc65dd update hyperparameters. 2023-03-29 13:07:28 -07:00
Rohan Taori
73cac8be49
Update README.md to clarify license 2023-03-25 15:30:01 -07:00
Xuechen Li
eb5b171d9b revise. 2023-03-17 13:25:25 -07:00
Rohan Taori
d3b79d0e95
Update README.md 2023-03-17 11:33:08 -07:00
Xuechen Li
c8ea92b1c3 remove failing eval. 2023-03-16 09:18:09 -07:00
Xuechen Li
7f0853214d document how training may slow down. 2023-03-16 00:43:24 -07:00
Yann Dubois
61a3b43245
Delete 2023-03-13-alpaca.md
Removing old blog version
2023-03-15 16:37:57 -07:00
Tianyi
bf04adbd38
Update README.md 2023-03-15 15:38:35 -07:00
Xuechen Li
38fade9806 add ack. 2023-03-15 11:49:54 -07:00
Xuechen Li
1807a44181 update ack. 2023-03-15 11:48:45 -07:00
Rohan Taori
3a50f614fc
Update README.md 2023-03-15 11:03:26 -07:00
Rohan Taori
9a14edbc84
Update gpu scaling batch size instructions 2023-03-15 09:43:23 -07:00
Xuechen Li
40d3d13996 fix typo in weight decay; clarify python version. 2023-03-15 09:35:19 -07:00
Yann Dubois
1a1af4d738
Remove duplicate blog 2023-03-15 04:00:37 -07:00
Xuechen Li
1ccc4dd6f3
Merge pull request #30 from tatsu-lab/train
[DEV] upload sanitized training code
2023-03-15 02:45:45 -07:00
Xuechen Li
6721f69ab3 comment. 2023-03-15 02:44:13 -07:00
Xuechen Li
e0cf6c690e add gitignore. 2023-03-15 02:38:18 -07:00
Xuechen Li
fa78c4fb25 training code. 2023-03-15 02:36:01 -07:00
Rohan Taori
7ad0c6b4f7
switch data license to cc by nc temporarily 2023-03-14 22:28:55 -07:00
Yann Dubois
576cdde57b
Update README.md 2023-03-14 18:13:44 -07:00
Rohan Taori
032f6e24f2
Merge pull request #18 from eltociear/patch-1
Update README.md
2023-03-14 17:46:30 -07:00
Rohan Taori
d4d4ba490f
Update README.md 2023-03-14 17:43:03 -07:00
Rohan Taori
c86c3f996c
readme typo 2023-03-14 16:31:38 -07:00
Rohan Taori
e3e2bd1944
add inference prompt to readme 2023-03-14 16:31:02 -07:00
Tianyi
be2b2da012
Update README.md 2023-03-14 14:41:15 -07:00
Ikko Eltociear Ashimine
f222e56f1f
Update README.md
huggingface -> Hugging Face
2023-03-14 17:55:50 +09:00
Yann Dubois
da37bb2eca add logo to blog 2023-03-13 09:56:12 -07:00
Yann Dubois
eb3f862bb9 add logo to blog 2023-03-13 08:21:37 -07:00
Tiiiger
f134962112 release 2023-03-13 08:15:01 -07:00