Commit Graph

  • 282edb9161 fix plot issues hiyouga 2024-03-12 18:41:35 +08:00
  • dff77004f2 support olmo hiyouga 2024-03-12 18:30:38 +08:00
  • 6c1b4aec75 fix #2802 hiyouga 2024-03-12 17:08:34 +08:00
  • 7814db1b42 fix #2803 hiyouga 2024-03-12 16:57:39 +08:00
  • c9ed3fc3a4 fix #2782 #2798 hiyouga 2024-03-12 15:53:29 +08:00
  • 9ee416a8fc Merge pull request #2743 from S3Studio/DockerizeSupport hoshi-hiyouga 2024-03-12 00:05:49 +08:00
  • 4f9a47c026 fix #2775 hiyouga 2024-03-11 00:42:54 +08:00
  • 3fcb1c6d09 tiny fix hiyouga 2024-03-11 00:17:18 +08:00
  • 7c492864e9 update parser hiyouga 2024-03-10 13:35:20 +08:00
  • 7ff8a064f3 support layerwise galore hiyouga 2024-03-10 00:24:11 +08:00
  • c635bbe465 fix #2732 hiyouga 2024-03-09 22:37:16 +08:00
  • 4881f4e631 allow non-packing pretraining hiyouga 2024-03-09 22:21:46 +08:00
  • c631799f5d fix #2766 hiyouga 2024-03-09 21:35:24 +08:00
  • 48846676d8 use default arg for freeze tuning hiyouga 2024-03-09 06:08:48 +08:00
  • f37d481c5d add GaLore results hiyouga 2024-03-09 04:11:55 +08:00
  • 5d7d8bd55c update hardware requirements hiyouga 2024-03-09 03:58:18 +08:00
  • 8ed1463236 update examples hiyouga 2024-03-09 02:30:37 +08:00
  • 43b2ede0f8 fix #2756 , patch #2746 hiyouga 2024-03-09 02:01:26 +08:00
  • 2f095e2017 Merge pull request #2746 from stephen-nju/main hoshi-hiyouga 2024-03-09 01:37:00 +08:00
  • 9b55bb964c Update setup.py hiyouga 2024-03-09 00:14:48 +08:00
  • 9b97b23ce7 fix aqlm version hiyouga 2024-03-09 00:09:09 +08:00
  • 53ab28533e fix example params hiyouga 2024-03-08 20:41:43 +08:00
  • 940c00e7ae update stephen_zhu 2024-03-08 12:47:44 +08:00
  • 18cfd5f349 fix ppo runtime error stephen 2024-03-08 11:48:26 +08:00
  • 6169df1c52 Add dockerize support S3Studio 2024-03-08 10:47:28 +08:00
  • d46c2bbcba update readme hiyouga 2024-03-08 03:06:21 +08:00
  • 48d4364586 fix chat engine, update webui hiyouga 2024-03-08 03:01:53 +08:00
  • 8042c66a76 Update setup.py hiyouga 2024-03-08 01:23:00 +08:00
  • 3879d79b89 update galore args hiyouga 2024-03-08 01:17:32 +08:00
  • e416cecf62 fix galore hiyouga 2024-03-08 00:44:51 +08:00
  • 81fcb80466 add Yi-9B model hiyouga 2024-03-07 23:11:57 +08:00
  • bf812fbe40 add galore examples hiyouga 2024-03-07 22:53:45 +08:00
  • 1e6fb6c8aa support galore hiyouga 2024-03-07 22:41:36 +08:00
  • 5d0c95bd02 update readme hiyouga 2024-03-07 20:34:49 +08:00
  • 7cd2417002 tiny fix hiyouga 2024-03-07 20:29:34 +08:00
  • 16851d66e5 Merge pull request #2739 from hiyouga/dev-vllm hoshi-hiyouga 2024-03-07 20:28:18 +08:00
  • 056d2d956a support vllm hiyouga 2024-03-07 20:26:31 +08:00
  • 9a69cadab3 fix #2735 hiyouga 2024-03-07 16:15:53 +08:00
  • 3de642bffd Merge pull request #2730 from cx2333-gt/main hoshi-hiyouga 2024-03-07 14:37:18 +08:00
  • 286b9d9849 revert choice name cx2333 2024-03-07 14:28:55 +08:00
  • cef1ede826 fix chatglm3 template hiyouga 2024-03-07 14:26:16 +08:00
  • 5007566588 fix flash_attn in train_web cx2333 2024-03-07 10:13:55 +08:00
  • e93fb3cc6c tiny fix hiyouga 2024-03-06 17:25:08 +08:00
  • 7578209735 export use balanced gpu hiyouga 2024-03-06 16:33:14 +08:00
  • 67f02f75d0 fix add tokens hiyouga 2024-03-06 15:04:02 +08:00
  • 73d9dfc7ab fix version checking hiyouga 2024-03-06 14:51:51 +08:00
  • 6b407092d9 update examples hiyouga 2024-03-06 13:14:57 +08:00
  • 3168abc0a1 fix arg dtype hiyouga 2024-03-05 20:53:30 +08:00
  • 46ee267cfc improve aqlm optim hiyouga 2024-03-05 20:49:50 +08:00
  • a10bead9b5 optimize aqlm training hiyouga 2024-03-05 18:35:41 +08:00
  • 3553e301dd fix dora inference hiyouga 2024-03-05 11:51:41 +08:00
  • 02b838b9b0 fix export model hiyouga 2024-03-05 11:05:41 +08:00
  • b1de6d1025 update readme hiyouga 2024-03-05 03:20:23 +08:00
  • bc67872218 add examples hiyouga 2024-03-05 03:16:35 +08:00
  • 0229fffde5 auto set chat template hiyouga 2024-03-05 02:41:20 +08:00
  • 3555b87363 update readme hiyouga 2024-03-04 19:29:26 +08:00
  • 2dca53962e fix export on cpu device hiyouga 2024-03-04 17:35:09 +08:00
  • f4f71f2797 fix sub-process error in thread hiyouga 2024-03-03 15:04:35 +08:00
  • 77ab9457ed update readme hiyouga 2024-03-03 01:41:07 +08:00
  • 4fa53b6282 update readme, add starcoder2, cosmopedia hiyouga 2024-03-03 01:01:46 +08:00
  • 790b73586b Update README_zh.md hoshi-hiyouga 2024-03-03 00:49:08 +08:00
  • 9c29c2a172 Update README.md hoshi-hiyouga 2024-03-03 00:48:47 +08:00
  • 863960d33e Update README.md hoshi-hiyouga 2024-03-03 00:48:06 +08:00
  • 330e5381b4 add colab demo hiyouga 2024-03-02 19:58:21 +08:00
  • 5bb411fdb8 move git files hiyouga 2024-03-02 18:30:11 +08:00
  • 59a9a5994e fix #2649 hiyouga 2024-03-01 13:02:41 +08:00
  • 5306a71b42 tiny fix hiyouga 2024-02-29 21:03:48 +08:00
  • 3eafa2dd9e fix webui hiyouga 2024-02-29 20:09:09 +08:00
  • 88fddb879d fix #2642 hiyouga 2024-02-29 18:32:54 +08:00
  • 71491825bf add twitter hiyouga 2024-02-29 17:45:30 +08:00
  • 30855b924a tiny fix hiyouga 2024-02-29 17:28:50 +08:00
  • 48d2e6d7fe tiny fix and release v0.5.3 hiyouga 2024-02-29 00:46:47 +08:00
  • 041c83ea03 Merge pull request #2575 from lungothrin/feature/chatter-with-role hoshi-hiyouga 2024-02-29 00:39:47 +08:00
  • 0e621c2dc9 fix #2629 hiyouga 2024-02-29 00:37:29 +08:00
  • 544e7a491b release v0.5.3 hiyouga 2024-02-29 00:34:19 +08:00
  • a2c881fa08 add examples hiyouga 2024-02-28 23:19:25 +08:00
  • c53c7af168 update chatglm3 template hiyouga 2024-02-28 21:11:23 +08:00
  • a2d93e5269 update readme hiyouga 2024-02-28 20:50:01 +08:00
  • b392e6cfb9 support DoRA, AWQ, AQLM #2512 hiyouga 2024-02-28 19:53:28 +08:00
  • 13aa2d389a support on fly test of tools Liang Ge 2024-02-23 23:55:47 +08:00
  • 1e7962dfc4 Merge pull request #2608 from Katehuuh/main hoshi-hiyouga 2024-02-27 16:49:34 +08:00
  • 1c9556c84c bump accelerate Katehuuh 2024-02-27 08:56:45 +01:00
  • ca3ca7a5b5 add pr template hiyouga 2024-02-26 18:31:07 +08:00
  • 0500befdb4 Create CONTRIBUTING.md hoshi-hiyouga 2024-02-26 18:23:03 +08:00
  • f618feab51 Create SECURITY.md hoshi-hiyouga 2024-02-26 18:03:17 +08:00
  • 4b06aa134f update readme hiyouga 2024-02-26 17:25:47 +08:00
  • 9cde56d760 Merge pull request #2531 from Rayrtfr/main hoshi-hiyouga 2024-02-26 16:36:45 +08:00
  • d0ea203694 Support Atom Model Rayrtfr 2024-02-21 18:35:03 +08:00
  • c5eb3fba62 update webui hiyouga 2024-02-25 20:23:41 +08:00
  • a8bc32553c update readme hiyouga 2024-02-25 16:26:08 +08:00
  • 88f3358320 Merge pull request #2525 from stephen-nju/main hoshi-hiyouga 2024-02-25 15:54:00 +08:00
  • a85bdcf2f6 add papers hiyouga 2024-02-25 15:34:47 +08:00
  • caf56b313e add papers hiyouga 2024-02-25 15:18:58 +08:00
  • 75603c45fc fix data entry hiyouga 2024-02-23 18:29:24 +08:00
  • 89f86cc970 fix gemma template hiyouga 2024-02-23 13:49:53 +08:00
  • c09a0e4f08 fix template hiyouga 2024-02-22 12:09:21 +08:00
  • 7bac6c9460 fix template hiyouga 2024-02-22 12:06:48 +08:00
  • 0c7d0bf172 support gemma hiyouga 2024-02-21 23:27:36 +08:00
  • a274900188 fix #2532 hiyouga 2024-02-21 21:55:14 +08:00
  • 67deefe527 tiny fix hiyouga 2024-02-21 18:30:29 +08:00