Commit Graph

  • ca548af2a2 remove rlhf support for chatglm2&3 hiyouga 2024-07-02 23:03:17 +08:00
  • 579997688f upcast logits hiyouga 2024-07-02 22:32:05 +08:00
  • e6ba7ef3e6 improve rlhf hiyouga 2024-07-02 22:23:08 +08:00
  • 20fdf177e8 move efficient_packing from data_args to model_args ancv 2024-07-02 18:37:55 +07:00
  • f0b01803ea Update bug-report.yml hiyouga 2024-07-02 19:18:56 +08:00
  • f5c4841ff2 Update bug-report.yml hiyouga 2024-07-02 19:16:12 +08:00
  • 1e01283d81 Merge pull request #4651 from hzhaoy/add-telechat-1b hoshi-hiyouga 2024-07-02 17:56:43 +08:00
  • 2196448c21 add TeleChat-1B hzhaoy 2024-07-02 17:49:04 +08:00
  • 96a81ce89d fix ppo callbacks hiyouga 2024-07-02 17:34:56 +08:00
  • a715490c2a Merge branch 'main' into main hoshi-hiyouga 2024-07-01 21:01:09 +08:00
  • 973cf8e980 tiny fix hiyouga 2024-07-01 05:43:17 +08:00
  • 4357e42391 tiny fix hiyouga 2024-07-01 03:55:20 +08:00
  • 884b49e662 add eval acc hiyouga 2024-07-01 03:51:20 +08:00
  • 38c94d2e9c Update label_issue.yml hiyouga 2024-07-01 01:29:09 +08:00
  • 67d2eb6b2a fix #4402 #4617 hiyouga 2024-07-01 01:19:27 +08:00
  • b670fb57db update readme hiyouga 2024-07-01 00:22:52 +08:00
  • 188b4be64d fix #4398 #4592 hiyouga 2024-06-30 21:28:51 +08:00
  • 889c042ecd update npu docker hiyouga 2024-06-30 21:05:31 +08:00
  • 3c4f8eaa55 loose gemma2 attention hiyouga 2024-06-29 01:42:14 +08:00
  • 6a75d57060 update readme hiyouga 2024-06-28 06:55:19 +08:00
  • fda2cf677b bf16 by default, gemma2 attns hiyouga 2024-06-28 06:00:26 +08:00
  • cfdf5a5a78 increase pissa_iter for stability hiyouga 2024-06-28 03:18:54 +08:00
  • a1437c15f7 fix docker flashattn hiyouga 2024-06-28 01:28:59 +08:00
  • 42e7489713 add Gemma2 models hiyouga 2024-06-28 01:26:50 +08:00
  • 024760f866 update examples hiyouga 2024-06-28 01:17:07 +08:00
  • 46f0189e88 refactor pissa, improve llamaboard hiyouga 2024-06-28 01:04:24 +08:00
  • edc7498111 Merge pull request #4580 from hzhaoy/bugfix-deepspeed-pissa hoshi-hiyouga 2024-06-28 00:46:51 +08:00
  • 9103fdf866 fix #4549 hiyouga 2024-06-28 00:41:58 +08:00
  • 95bf795de4 fix docker file hiyouga 2024-06-27 20:29:16 +08:00
  • bf99223a80 tiny fix hiyouga 2024-06-27 20:14:48 +08:00
  • 9caf9b6f91 Merge pull request #4590 from injet-zhou/main hoshi-hiyouga 2024-06-27 20:09:36 +08:00
  • 727c7b0dc6 Merge pull request #4461 from hzhaoy/feature/support-flash-attn hoshi-hiyouga 2024-06-27 20:05:26 +08:00
  • 13d184b280 Merge pull request #4561 from hashstone/fix-docker-npu hoshi-hiyouga 2024-06-27 19:58:16 +08:00
  • 12a91774b0 Update Dockerfile hoshi-hiyouga 2024-06-27 19:57:40 +08:00
  • 88018000ac Update Dockerfile hoshi-hiyouga 2024-06-27 19:51:25 +08:00
  • f6eda1c35d Update setup.py hoshi-hiyouga 2024-06-27 19:38:15 +08:00
  • a2ebdbc112 Update README_zh.md hoshi-hiyouga 2024-06-27 19:17:52 +08:00
  • e930a42083 Update README.md hoshi-hiyouga 2024-06-27 19:17:35 +08:00
  • 4b123f49cb Update setup.py hoshi-hiyouga 2024-06-27 19:16:46 +08:00
  • 556eca918d Exit the process with the subprocess's return code when utilizing the CLI faddddeout 2024-06-27 09:58:00 +00:00
  • 31fcd03f3c support docker-npu-[amd64|arm64] build fanjunliang 2024-06-27 15:21:55 +08:00
  • 89d9dd5aa5 fix #4579 hzhaoy 2024-06-27 13:49:57 +08:00
  • d1aad72826 add quant checks hiyouga 2024-06-27 01:12:25 +08:00
  • 8e5b4bddf4 update examples hiyouga 2024-06-27 00:53:33 +08:00
  • 5a7cb9af4e tiny fix hiyouga 2024-06-27 00:46:41 +08:00
  • d1cda4ec68 tiny fix hiyouga 2024-06-27 00:36:04 +08:00
  • 8aaf1185a5 support HQQ/EETQ #4113 hiyouga 2024-06-27 00:29:42 +08:00
  • b46bd07119 add flash-attn installation flag in Dockerfile hzhaoy 2024-06-27 00:11:04 +08:00
  • 08fa707085 improve autogptq integration hiyouga 2024-06-26 22:11:44 +08:00
  • 72ba29d81a fix #4458 hiyouga 2024-06-26 19:52:35 +08:00
  • cf2dc4c444 fix #4556 hiyouga 2024-06-26 19:43:16 +08:00
  • d82d86e16d fix torch-npu dependency fanjunliang 2024-06-26 18:21:42 +08:00
  • bde31d8600 Merge pull request #4544 from MengqingCao/npu hoshi-hiyouga 2024-06-26 10:19:24 +08:00
  • e115d55585 fix docker-compose path MengqingCao 2024-06-26 02:15:00 +00:00
  • daea86e047 support flash-attn in Dockerfile hzhaoy 2024-06-25 15:13:07 +08:00
  • a4f69d8914 fix #4456 hiyouga 2024-06-25 14:34:13 +08:00
  • 98f382fda3 lint hiyouga 2024-06-25 02:55:50 +08:00
  • cd899734f3 fix test case hiyouga 2024-06-25 02:51:49 +08:00
  • f51b435bcf fix #4432 hiyouga 2024-06-25 02:34:04 +08:00
  • 0f82a55305 fix #4379 hiyouga 2024-06-25 02:31:44 +08:00
  • 9fd7a410bb tiny fix about badam hiyouga 2024-06-25 01:54:53 +08:00
  • 98fb3d015a fix #4419 hiyouga 2024-06-25 01:51:29 +08:00
  • bfb2ad7c79 Merge pull request #4352 from Ledzy/main hoshi-hiyouga 2024-06-25 01:49:13 +08:00
  • 135bfbf7c1 tiny fix hiyouga 2024-06-25 01:15:19 +08:00
  • c6b17ebc20 Merge pull request #4355 from MengqingCao/npu hoshi-hiyouga 2024-06-25 01:07:43 +08:00
  • b55eb30474 Update README_zh.md hoshi-hiyouga 2024-06-25 01:06:59 +08:00
  • cec2f1fc00 Update README.md hoshi-hiyouga 2024-06-25 01:03:38 +08:00
  • 8367ec03a7 Update docker-compose.yml hoshi-hiyouga 2024-06-25 00:54:28 +08:00
  • 37013f8068 Update Dockerfile hoshi-hiyouga 2024-06-25 00:50:34 +08:00
  • 8360544d65 Update docker-compose.yml hoshi-hiyouga 2024-06-25 00:46:47 +08:00
  • b5cdef43a1 Update Dockerfile hoshi-hiyouga 2024-06-25 00:46:08 +08:00
  • 2e5d521ed8 Update Dockerfile hoshi-hiyouga 2024-06-24 23:41:35 +08:00
  • dbe35d52d1 Merge pull request #4409 from kno10/patch-2 hoshi-hiyouga 2024-06-24 23:21:31 +08:00
  • 8bcdb6f52c Update cli.py hoshi-hiyouga 2024-06-24 23:21:10 +08:00
  • 5cfcb8262e Merge pull request #4417 from mMrBun/main hoshi-hiyouga 2024-06-24 23:17:55 +08:00
  • 0b331a318b Update test_formatter.py hoshi-hiyouga 2024-06-24 23:14:36 +08:00
  • 5d6cf55208 Update template.py hoshi-hiyouga 2024-06-24 23:12:59 +08:00
  • 9a1ec19845 Update loader.py hoshi-hiyouga 2024-06-24 23:06:18 +08:00
  • a79e93f335 fix #4410 hiyouga 2024-06-24 22:34:31 +08:00
  • abcb94a738 Merge pull request #4445 from MengqingCao/label hoshi-hiyouga 2024-06-24 22:02:05 +08:00
  • a4f2d5aa6f Update label_issue.yml hoshi-hiyouga 2024-06-24 22:01:23 +08:00
  • 6b738d1c89 Update label_issue.yml hoshi-hiyouga 2024-06-24 21:59:39 +08:00
  • f4c518b370 Merge pull request #4446 from stceum/bug-fix hoshi-hiyouga 2024-06-24 21:41:28 +08:00
  • d475dd3809 Update parser.py hoshi-hiyouga 2024-06-24 21:37:42 +08:00
  • 5675c47a01 Update test_attention.py hoshi-hiyouga 2024-06-24 21:35:34 +08:00
  • 16e950454e Bug Fix: off is parsed as False in yaml file, changed to disabled to avoid this. stceum 2024-06-24 20:39:20 +08:00
  • 2926265a14 auto-label npu issue MengqingCao 2024-06-24 12:27:00 +00:00
  • af2607de1a update docker files MengqingCao 2024-06-24 10:57:36 +00:00
  • 826d7808b4 update readme hiyouga 2024-06-24 18:29:04 +08:00
  • 4c89aca243 update readme hiyouga 2024-06-24 18:22:12 +08:00
  • 43a065bb07 Add tool_format to overwrite tool formatter template mMrBun 2024-06-22 02:00:13 +08:00
  • 4513a2cc75 remove dup template hiyouga 2024-06-22 01:31:32 +08:00
  • f29c1ac6e5 fix api hiyouga 2024-06-22 00:00:38 +08:00
  • 05abe47c8b Print help if no arguments given Erich Schubert 2024-06-21 09:14:21 +02:00
  • 6c185a2c57 move configure_packing to llamafactory.model.patcher and fix constants ancv 2024-06-21 00:45:06 +07:00
  • af2cb33bb2 tiny fix hiyouga 2024-06-20 22:56:05 +08:00
  • f16a4a8264 Merge pull request #4382 from MengqingCao/bugfix hoshi-hiyouga 2024-06-20 10:19:37 +08:00
  • b232552d42 update dependencies MengqingCao 2024-06-20 02:09:47 +00:00
  • 0edccc11a5 improve llamaboard hiyouga 2024-06-19 23:46:03 +08:00
  • b2f5c0e0db fix llamaboard abort hiyouga 2024-06-19 23:22:28 +08:00