Commit Graph

219 Commits

Author SHA1 Message Date
hiyouga a1c8c98c5f fix #2941 2024-03-24 00:28:44 +08:00
0xez 675ba41562
Update README.md, fix the release date of the paper 2024-03-21 22:14:48 +08:00
hiyouga 5eaa50fa01 add citation 2024-03-21 17:04:10 +08:00
hiyouga 0581bfdbc7 paper release 2024-03-21 13:49:17 +08:00
hiyouga bfe7a91289 update readme 2024-03-21 00:48:42 +08:00
hiyouga 8408225162 support fsdp + qlora 2024-03-21 00:36:06 +08:00
hiyouga 9bec3c98a2 fix #2777 #2895 2024-03-20 17:59:45 +08:00
khazic 0531dac30d Updated README with new information 2024-03-20 14:21:16 +08:00
刘一博 df9b4fb90a Updated README with new information 2024-03-20 14:11:28 +08:00
hiyouga 72367307df improve lora+ impl. 2024-03-13 23:32:51 +08:00
hiyouga b3247d6a16 support olmo 2024-03-12 18:30:38 +08:00
hoshi-hiyouga c901aa63ff
Merge pull request #2743 from S3Studio/DockerizeSupport
Add dockerize support
2024-03-12 00:05:49 +08:00
hiyouga 8664262cde support layerwise galore 2024-03-10 00:24:11 +08:00
hiyouga 818726e9bc add GaLore results 2024-03-09 04:11:55 +08:00
hiyouga 393c2de27c update hardware requirements 2024-03-09 03:58:18 +08:00
hiyouga 10be2f0ecc fix aqlm version 2024-03-09 00:09:09 +08:00
S3Studio 3d911ae713 Add dockerize support
Already tested with the model of Qwen:1.8B and the dataset of alpaca_data_zh. Some python libraries are added to the Dockerfile as a result of the exception messages displayed throughout test procedure.
2024-03-08 10:47:28 +08:00
hiyouga 4a2cc60b94 update readme 2024-03-08 03:06:21 +08:00
hiyouga 33a4c24a8a fix galore 2024-03-08 00:44:51 +08:00
hiyouga 57452a4aa1 add Yi-9B model 2024-03-07 23:11:57 +08:00
hiyouga 7230e1177d add galore examples 2024-03-07 22:53:45 +08:00
hiyouga 28f7862188 support galore 2024-03-07 22:41:36 +08:00
hiyouga 725f7cd70f update readme 2024-03-07 20:34:49 +08:00
hiyouga 77211d9843 tiny fix 2024-03-07 20:29:34 +08:00
hiyouga d07ad5cc1c support vllm 2024-03-07 20:26:31 +08:00
hiyouga 0048a2021e tiny fix 2024-03-06 17:25:08 +08:00
hiyouga 9658c63cd9 fix add tokens 2024-03-06 15:04:02 +08:00
hiyouga 3016e65657 fix version checking 2024-03-06 14:51:51 +08:00
hiyouga df9e6bb063 update readme 2024-03-05 03:20:23 +08:00
hiyouga 24a79bd50f update readme 2024-03-04 19:29:26 +08:00
hiyouga 7c227e07dd update readme 2024-03-03 01:41:07 +08:00
hiyouga 894d183214 update readme, add starcoder2, cosmopedia 2024-03-03 01:01:46 +08:00
hoshi-hiyouga 4bf7eb72e0
Update README.md 2024-03-03 00:48:47 +08:00
hoshi-hiyouga 585c884ea9
Update README.md 2024-03-03 00:48:06 +08:00
hiyouga 318315c76d add colab demo 2024-03-02 19:58:21 +08:00
hiyouga bb16502c33 add twitter 2024-02-29 17:45:30 +08:00
hiyouga fa5ab21ebc release v0.5.3 2024-02-29 00:34:19 +08:00
hiyouga 804c1e7083 add examples 2024-02-28 23:19:25 +08:00
hiyouga 38d8b2cef8 update chatglm3 template 2024-02-28 21:11:23 +08:00
hiyouga a2dccce06a update readme 2024-02-28 20:50:01 +08:00
hiyouga cfefacaa37 support DoRA, AWQ, AQLM #2512 2024-02-28 19:53:28 +08:00
hiyouga 3ba1054593 update readme 2024-02-26 17:25:47 +08:00
hiyouga 261f631a1c update readme 2024-02-25 16:26:08 +08:00
hiyouga aca948da8f add papers 2024-02-25 15:34:47 +08:00
hiyouga ad76482cf9 add papers 2024-02-25 15:18:58 +08:00
hiyouga c99e19641a support gemma 2024-02-21 23:27:36 +08:00
hiyouga daa3185350 tiny fix 2024-02-21 18:30:29 +08:00
hoshi-hiyouga 869fd208a8
Update README.md 2024-02-20 16:07:55 +08:00
codemayq d47e40633a 1. update the version of pre-built bitsandbytes library
2. add pre-built flash-attn library
2024-02-20 11:28:25 +08:00
codemayq 95f53a46bd 1. update the version of pre-built bitsandbytes library
2. add pre-built flash-attn library
2024-02-20 11:26:22 +08:00