747 Commits

Author SHA1 Message Date
liu-zichen
75dfe259cf fix lr not change
Former-commit-id: 387dd2d51b5d8cd666459040fdd16525b34720d9
2024-08-13 16:33:34 +08:00
“Wzw”
e734222373 fix Llama-template's system prompt bug
Former-commit-id: 2e3eddcd0918b0c968ded0df7c82e3dcff870381
2024-08-12 19:22:12 +08:00
hiyouga
7fb61bad04 add qwen2 math models
Former-commit-id: 72ff43a1772c9de5ff914d5e1c8bdc8dea9ae0c8
2024-08-09 20:20:35 +08:00
hiyouga
59cbce1a46 add adam_mini to readme
Former-commit-id: d610c6bcf8a8ba6f4236f5d11f79571b83f4fb11
2024-08-09 20:02:03 +08:00
hoshi-hiyouga
7e755e9cac Merge pull request #5095 from relic-yuexi/feat-optimizer
Feat optimizer

Former-commit-id: f08390d252d42a812b71a08daba7339cc40889b7
2024-08-09 19:51:33 +08:00
hiyouga
5af32ce705 follow #5115
Former-commit-id: 7d917e03e2df570139bae18227d9c7303a12de2a
2024-08-09 18:03:00 +08:00
hoshi-hiyouga
4e8861e653 Merge pull request #5115 from YeQiuO/main
fix: `Train on the last turn only` truncate bug
Former-commit-id: 2c6dae45f7a7b72c961489ac407b1b444ab7752e
2024-08-09 17:58:27 +08:00
hoshi-hiyouga
46f834ec75 Update template.py
Former-commit-id: ae2a5221c109ae3474d219c37433be767abbee91
2024-08-09 16:27:42 +08:00
“Wzw”
6ec64a7e56 mask_history args verify valid
Former-commit-id: 2f8388b4f4195d934400ad9267d72e10ca4105a3
2024-08-08 10:12:01 +08:00
“Wzw”
d71446e387 fix mask_history tiny bug
Former-commit-id: cac07aac6196be026f723b2397a343d4fb675973
2024-08-08 10:09:33 +08:00
moontidef
8f42d7df56 feat: add support for adammini
Former-commit-id: a2d5fafb705ff44db1711e972490f0abebc2012b
2024-08-07 10:08:22 +08:00
moontidef
33a90b9026 fix: rename optimzer to optimizer
Former-commit-id: 186dc1fde822e6a603ac273538741ea3853f243e
2024-08-07 10:05:01 +08:00
moontidef
710902b0d0 Merge branch 'hiyouga:main' into main
Former-commit-id: d1b23283e0e4286f126d38d7bdc55802f74c8922
2024-08-06 00:18:45 +08:00
moontidef
7b4f5d3b21 fix: fix the deepseekcoder template to avoid repeat problem
Former-commit-id: 56294831115f095135f72490a8a435434b2f0a11
2024-08-05 23:55:45 +08:00
hiyouga
13093963b1 fix #5048
Former-commit-id: 71a6861667ae68c1fd6a69acf68e1359b858cf1b
2024-08-05 23:48:19 +08:00
codingma
4b6252151e support gemma-2-2b
Former-commit-id: 7037192cf6049fd7d675aed4a6237ed929c6b170
2024-08-01 13:45:48 +08:00
hoshi-hiyouga
f3765d1996 Merge pull request #5010 from Eruly/main
Add Korean web UI (llamafactory-cli webui)

Former-commit-id: 2050806aa826028df45c0c746b4314afe178dcd3
2024-07-30 01:55:54 +08:00
eruly
9fdf800750 Add Korean web UI (llamafactory-cli webui)
Former-commit-id: 357a035f2aeb9548368c230c5a17dcdfa4844b17
2024-07-29 13:47:13 +00:00
codingma
75e80fa820 fix pissa save
Former-commit-id: 25a1dad7c8df79c15efecb8c6f871a13a327f57a
2024-07-29 10:44:34 +08:00
hoshi-hiyouga
9f74d36ba4 Merge pull request #4892 from piamo/main
update deepseek template

Former-commit-id: 3233efc8404972098665286d9dec7312dd6ecfab
2024-07-26 11:49:34 +08:00
hoshi-hiyouga
fc2435f135 Merge pull request #4950 from liuwwang/main and fi
fix: Repair the issue where quantization failed after merging the adapter.
Former-commit-id: 93a68ea1f4372973f745a2c250250ecaac515e27
2024-07-26 11:48:56 +08:00
hiyouga
28b5f656db update webui
Former-commit-id: 463edec1b1c1345afc791e225deb33f118f3582e
2024-07-24 21:11:51 +08:00
hiyouga
211038584a tiny fix
Former-commit-id: 28cac0e325bfd7a6c0c344ad2d46511613190cd7
2024-07-24 18:33:39 +08:00
hiyouga
ff5ba97970 fix #4928
Former-commit-id: 6d557e8959678f9d4edbcb3d5a6dfba14b429b18
2024-07-24 17:00:29 +08:00
hiyouga
5c6d88e91c add mistral nemo model
Former-commit-id: 428bb49f53b32947bc0a62ca19ab10844154c07c
2024-07-24 16:25:53 +08:00
hiyouga
0a04d9470f add llama3.1
Former-commit-id: 3c433890f9b61c520572f5233aae70584da0f330
2024-07-24 16:20:11 +08:00
Liuww
f0408c0dde fix: Repair the issue where quantization failed after merging the adapter.
Former-commit-id: 8109561b7f577d448f8bca7e569f7f443cf6bb52
2024-07-24 14:31:29 +08:00
hiyouga
a041f4a111 tiny fix
Former-commit-id: bf6a2f032c598f969708c1c3db4875d6239c41a9
2024-07-22 21:10:15 +08:00
hoshi-hiyouga
cdf9dae53e fix #4917
Former-commit-id: e26919aafd8436489d065789c9c25d72c8d05a6d
2024-07-22 11:28:31 +08:00
hiyouga
1917f431f5 tiny fix
Former-commit-id: 9133316e558a3c8744f5eb6ab8678686bf4859ed
2024-07-22 00:06:03 +08:00
hiyouga
a770afbff2 fix flashattn + packing
Former-commit-id: 4adc6ce4abc718c25f39b316bfc3352d0d01ed1e
2024-07-21 17:07:45 +08:00
huangpan.foo
b1a5bf025b update deepseek template
Former-commit-id: f5ca86ec95bb301df42ffaa6923fc3037a224e34
2024-07-19 15:02:54 +08:00
hiyouga
adff3e5050 set dev version
Former-commit-id: 0b9a2275dc533b65578278f979ce053e95a644b3
2024-07-19 02:01:46 +08:00
hiyouga
0e88c5754f update parser
Former-commit-id: 5262c8702382ff8bc36a172387bc4c8949f326ea
2024-07-19 01:36:39 +08:00
hiyouga
3fff875f99 release v0.8.3
Former-commit-id: 7180a3b99c3c218dfb0dc607ad5e87219269a678
2024-07-19 01:21:18 +08:00
hiyouga
994b9089e9 add unittest
Former-commit-id: 8a1f0c5f922989e08a19c65de0b2c4afd2a5771f
2024-07-19 01:06:27 +08:00
hiyouga
4c1513a845 follow #4878 fix #4684
Former-commit-id: 4715e5c5b8040b21e5f401f7e969b9fd2757d520
2024-07-18 22:06:12 +08:00
Shiyu Zhang
c1e1918db1 仅仅训练最后一轮对话
Former-commit-id: ab6198e4c099edeb1a400f58729cd617e8cd8e50
2024-07-18 15:30:25 +08:00
hiyouga
341225a405 fix metrics #4786
Former-commit-id: 7d0c4bd394fc3cba197db1719f1164b9dd66ac21
2024-07-17 00:47:00 +08:00
hiyouga
8c93921952 support batch_eval_metrics, fix #4826
Former-commit-id: 3fe1df17188825f8a32fbe6a1294b4b532ce0c85
2024-07-17 00:33:00 +08:00
hiyouga
45367105fc tiny fix
Former-commit-id: 952807b16cd85fa193a05a83b1a735a6b06abc82
2024-07-15 23:09:50 +08:00
hoshi-hiyouga
757573bec1 Merge pull request #4821 from codemayq/feature-eval-split
add "split" as suffix in eval task name

Former-commit-id: 5b6033eef3c2cfd5b47bb67e0d803d8de68f3ff0
2024-07-15 22:59:44 +08:00
hiyouga
1891b64072 fix #4820
Former-commit-id: 8c0f8357e1eebee32010fe715554f1136b68b4ba
2024-07-15 22:32:07 +08:00
codingma
0ea708c226 1. change the task name format
2. delete split param in data_args.py


Former-commit-id: 309d30efe24785912ff751fc573677875fc5819e
2024-07-15 09:55:33 +08:00
hiyouga
cb474c7b11 allow computing rouge in training
Former-commit-id: ac67d50673989e8137965f5f718fec67c184f55b
2024-07-15 01:16:26 +08:00
hiyouga
e4d11a117b fix up
Former-commit-id: 43a56cb331fae899ca35b0c312730d4ab79d0c42
2024-07-15 01:04:56 +08:00
hoshi-hiyouga
68365045b4 Merge pull request #4691 from codemayq/feature-suppot-eval-dataset
add eval dataset support

Former-commit-id: 51eb379b44fad0336fc96c329ec98dc4528b9c2c
2024-07-15 01:00:34 +08:00
hoshi-hiyouga
502555b65d Update data_args.py
Former-commit-id: c3cee10294d56a1bc226871819b3a725b09aa67e
2024-07-15 00:56:03 +08:00
hoshi-hiyouga
0bc52c0aae Update preprocess.py
Former-commit-id: da92f4a1b9c12a8e2489b964baba5e2c8e739ef1
2024-07-15 00:55:36 +08:00
hoshi-hiyouga
6bf2663b8e Update parser.py
Former-commit-id: 145687997c86b8785e37dd60fbb9f3a5986730a6
2024-07-15 00:55:21 +08:00