Commit Graph

  • 823f618cba update project_kwargs for ppo config stephen 2024-02-21 13:47:38 +08:00
  • bc16c9a54a support lora for llama pro hiyouga 2024-02-21 02:17:22 +08:00
  • a3f30038a0 fix #2516 hiyouga 2024-02-20 20:44:24 +08:00
  • e237f618c2 Merge pull request #2514 from codemayq/main hoshi-hiyouga 2024-02-20 16:09:25 +08:00
  • 688adad665 Update README.md hoshi-hiyouga 2024-02-20 16:07:55 +08:00
  • 0158812afb Update README_zh.md hoshi-hiyouga 2024-02-20 16:06:59 +08:00
  • e52e0d9b07 1. update the version of pre-built bitsandbytes library 2. add pre-built flash-attn library codemayq 2024-02-20 11:28:25 +08:00
  • eb2aa2c073 1. update the version of pre-built bitsandbytes library 2. add pre-built flash-attn library codemayq 2024-02-20 11:26:22 +08:00
  • debfd46749 release v0.5.2 v0.5.2 hiyouga 2024-02-20 11:12:43 +08:00
  • 5ccf8fcd6b update webui hiyouga 2024-02-19 16:49:58 +08:00
  • 7bd1991513 add test scripts hiyouga 2024-02-19 02:09:13 +08:00
  • 456e4ca569 fix safetensors hiyouga 2024-02-18 18:12:16 +08:00
  • 6bf0fe4913 fix #2481 hiyouga 2024-02-15 19:07:47 +08:00
  • 596b6828cb support llama pro #2338 , add rslora hiyouga 2024-02-15 02:27:36 +08:00
  • b403f8d8a8 Merge pull request #2474 from younesbelkada/add-hf-tags hoshi-hiyouga 2024-02-14 10:26:03 +08:00
  • 590b6c2143 add v1 hf tags younesbelkada 2024-02-13 05:58:49 +00:00
  • 5537ef1e7d fix #2471 hiyouga 2024-02-12 21:07:46 +08:00
  • 5f83860aa1 add option to disable version check hiyouga 2024-02-10 22:31:23 +08:00
  • 62b6a7971a update data/readme hiyouga 2024-02-10 21:04:29 +08:00
  • 1d16e87c5f update default template hiyouga 2024-02-10 16:44:47 +08:00
  • 1955a8ea5a improve aligner hiyouga 2024-02-10 16:39:19 +08:00
  • a41fa6e730 Merge pull request #2462 from mnmueller/main hoshi-hiyouga 2024-02-09 22:55:48 +08:00
  • b98a64448a improve fix tokenizer hiyouga 2024-02-09 14:53:14 +08:00
  • 1ce82f391a Slim Orca data parsing Mark Mueller 2024-02-08 19:32:20 +01:00
  • 4d473894fd Slim Orca data parsing Mark Mueller 2024-02-08 17:56:18 +01:00
  • 5788b7c7d0 Slim Orca data parsing Mark Mueller 2024-02-08 17:54:18 +01:00
  • 04515f6b55 Slim Orca data parsing Mark Mueller 2024-02-08 17:52:36 +01:00
  • 96f8ccf3d5 SlimOrca aligner Mark Mueller 2024-02-08 08:28:32 -08:00
  • 2c3ef480a6 Merge pull request #2423 from mayflower/main hoshi-hiyouga 2024-02-07 15:58:20 +08:00
  • fa6873122c Update tests.yml hiyouga 2024-02-07 01:18:22 +08:00
  • 34bc0c22b1 lint hiyouga 2024-02-07 01:10:04 +08:00
  • e5484b2729 Update pyproject.toml hiyouga 2024-02-07 00:45:58 +08:00
  • f67f781fed update gc kwargs hiyouga 2024-02-07 00:38:24 +08:00
  • b564b97b7e fix #2438 hiyouga 2024-02-06 15:23:08 +08:00
  • 0dd68d1e06 add models hiyouga 2024-02-06 14:57:23 +08:00
  • 73f40f1ca4 support qwen1.5 hiyouga 2024-02-06 00:10:51 +08:00
  • ea53bebac4 fix #2436 hoshi-hiyouga 2024-02-05 22:55:28 +08:00
  • 00418012bd Update test_toolcall.py hoshi-hiyouga 2024-02-05 22:51:03 +08:00
  • 5f3d8c514b Update test_toolcall.py hoshi-hiyouga 2024-02-05 22:50:43 +08:00
  • cb39a3f1c4 Update test_toolcall.py tao.jun 2024-02-05 20:49:23 +08:00
  • 4d78fe6ece Merge branch 'hiyouga:main' into main Johann-Peter Hartmann 2024-02-04 13:55:00 +00:00
  • a3e3ea9846 fix #2421 hiyouga 2024-02-04 21:02:55 +08:00
  • feba34e82d Merge branch 'hiyouga:main' into main Johann-Peter Hartmann 2024-02-04 12:51:25 +00:00
  • e134013e04 fix reserved label len hiyouga 2024-02-04 17:54:26 +08:00
  • 5589d0296a fix #2420 hiyouga 2024-02-04 15:51:47 +08:00
  • de0ebab464 fix #2189 hiyouga 2024-02-04 00:47:37 +08:00
  • f2e7122a96 bump up transformers version hiyouga 2024-02-04 00:01:16 +08:00
  • 996cc5d900 fix #2397 hiyouga 2024-02-03 23:45:31 +08:00
  • a2ae5bd867 add hint for freeze #2412 hiyouga 2024-02-03 23:38:56 +08:00
  • 5fa52e87cb fix #2376 hiyouga 2024-02-03 23:14:31 +08:00
  • bcd76d2c7a support minicpm #2404 hiyouga 2024-02-03 22:36:46 +08:00
  • 36fcbedc11 add simple german chatml template chatml_de Johann-Peter Hartmann 2024-02-03 09:01:15 +01:00
  • 1dad01cc53 Merge branch 'hiyouga:main' into main Johann-Peter Hartmann 2024-02-03 08:43:12 +01:00
  • 5fb21f6e54 Merge pull request #2411 from lxsyz/main hoshi-hiyouga 2024-02-02 17:38:16 +08:00
  • 08dfac8352 fix eos_token_id=0 bug Fallen Angel 2024-02-02 17:34:48 +08:00
  • 956751e419 Merge branch 'hiyouga:main' into main Johann-Peter Hartmann 2024-01-31 14:05:52 +01:00
  • fe2ae04c91 fix #2388 hiyouga 2024-01-31 17:23:56 +08:00
  • 5b8712d061 fix autoset attn impl, update data readme hiyouga 2024-01-31 11:58:07 +08:00
  • dc7ff90c1e Add support for german datasets Johann-Peter Hartmann 2024-01-30 10:18:01 +01:00
  • 1ace676170 fix #2320 hiyouga 2024-01-24 16:19:18 +08:00
  • 8947a87b95 Merge pull request #2319 from ftgreat/main hoshi-hiyouga 2024-01-24 15:32:26 +08:00
  • 786a2f1103 Add patch_mixtral_replace_moe_impl for full training Mitral using DeepSpeed Zero3. ldwang 2024-01-24 15:25:31 +08:00
  • 36ac14a566 Add patch_mixtral_replace_moe_impl for full training Mitral using DeepSpeed Zero3. ldwang 2024-01-24 14:43:16 +08:00
  • 7a048fc91d add hint hiyouga 2024-01-22 23:32:01 +08:00
  • 3f3756b113 Merge pull request #2283 from A-Cepheus/main hoshi-hiyouga 2024-01-22 23:28:45 +08:00
  • b36c4b99cc Update patcher.py hoshi-hiyouga 2024-01-22 23:27:39 +08:00
  • 9856a2276e Update tests.yml hoshi-hiyouga 2024-01-22 23:22:15 +08:00
  • b6dc3ed3ad Create tests.yml hoshi-hiyouga 2024-01-22 23:13:04 +08:00
  • 75be329994 fix #2282 and update tool prompt hiyouga 2024-01-22 22:27:30 +08:00
  • 1fe1ca1c8b add orion models hiyouga 2024-01-22 21:26:53 +08:00
  • 882a6a1d51 🐞 fix: typo A-Cepheus 2024-01-22 16:04:39 +08:00
  • 712ab4ae7a 🐞 fix: typo, move MoE fix to patcher A-Cepheus 2024-01-22 16:01:58 +08:00
  • 18ad259fb3 fix: ZeRO3 does not work with MoE models Former-commit-id: b2844c049a88ea89f8e1812e2d2e8662b4002965 A-Cepheus 2024-01-22 15:21:14 +08:00
  • fe4d93c6db add array param format hiyouga 2024-01-21 22:17:48 +08:00
  • c6ba588e37 update tool test hiyouga 2024-01-21 19:41:46 +08:00
  • 3fda60fca0 fix api hiyouga 2024-01-21 19:15:27 +08:00
  • 96531a0ef8 fix #2268 hiyouga 2024-01-21 14:11:38 +08:00
  • 7abc3065fb tiny fix hiyouga 2024-01-21 13:26:12 +08:00
  • 013ded4bac Merge pull request #2266 from yhyu13/fix_export_model_dtype hoshi-hiyouga 2024-01-21 12:40:39 +08:00
  • 010c3c7348 Merge branch 'main' into fix_export_model_dtype hoshi-hiyouga 2024-01-21 12:40:24 +08:00
  • bf075c075c Update tuner.py hoshi-hiyouga 2024-01-21 12:39:38 +08:00
  • 41b34e5f60 Merge pull request #2262 from fenglui/main hoshi-hiyouga 2024-01-21 12:34:37 +08:00
  • 5a889398e7 format hiyouga 2024-01-21 12:34:17 +08:00
  • 054cae86d8 Merge pull request #2264 from seoeaa/main hoshi-hiyouga 2024-01-21 12:25:24 +08:00
  • cd1cb8b83c Remove manully set use_cache; torch_dtype is not str, save model as bfloat16 used to fail; yhyu13 2024-01-21 11:12:15 +08:00
  • a34779c027 add russian lang Aleksandr 2024-01-21 04:28:14 +03:00
  • d19cb77d74 fix torch_dtype check of export_model fenglui 2024-01-21 05:01:53 +08:00
  • ab67528e89 release v0.5.0 (real) v0.5.0 hiyouga 2024-01-21 01:54:49 +08:00
  • 27f281480a finish agent hiyouga 2024-01-21 01:47:33 +08:00
  • 50459a39f4 fix api hiyouga 2024-01-21 00:03:09 +08:00
  • 5c9815ef6f fix internlm2 template hiyouga 2024-01-20 23:33:50 +08:00
  • aed00a97b6 fix cli_demo hiyouga 2024-01-20 23:27:10 +08:00
  • 7543dc4a9d fix #2260 hiyouga 2024-01-20 23:22:09 +08:00
  • 841fa0030f release v0.5.0 hiyouga 2024-01-20 20:21:39 +08:00
  • 66e0e651b9 format style hiyouga 2024-01-20 20:15:56 +08:00
  • 1750218057 fix tests hiyouga 2024-01-20 19:58:04 +08:00
  • 80637fc06d support longlora for main branch hiyouga 2024-01-20 19:25:22 +08:00
  • 8efc055511 Merge pull request #2201 from liu-zichen/token_embed_resize hoshi-hiyouga 2024-01-20 17:45:38 +08:00
  • be61bfda93 add upcast_lmhead option hiyouga 2024-01-19 23:54:25 +08:00
  • 1a39f529c0 set use_reentrant=False hiyouga 2024-01-19 23:29:54 +08:00