1963 Commits

Author SHA1 Message Date
hiyouga
019c6dad84 fix #4925
Former-commit-id: 935b22d93ed461e829cd1e6201de1fea697f4d1e
2024-07-24 16:56:58 +08:00
hiyouga
fae881b854 fix #4944
Former-commit-id: 1bbd49faaef438f49cb5340166cb13faee8fb854
2024-07-24 16:42:51 +08:00
hiyouga
91e54d458f add mistral nemo model
Former-commit-id: 1550fe7331370ad39e8ed69c1b060ead902a77e4
2024-07-24 16:25:53 +08:00
hiyouga
e0875f82b3 add llama3.1
Former-commit-id: 26533c0604ef765170f93986bc06f3066c5e28ee
2024-07-24 16:20:11 +08:00
hiyouga
d4440c07b6 Update wechat_npu.jpg
Former-commit-id: bb0a37dc067e4385290644f165e3634dcbd88894
2024-07-22 21:17:22 +08:00
hiyouga
1cddf80a97 tiny fix
Former-commit-id: 5665062ca0bfb166cd8f2e896e2b0970037373f6
2024-07-22 21:10:15 +08:00
hoshi-hiyouga
37c6a0c6dc fix #4917
Former-commit-id: 26082fc6c90e6a399ae5b44f2c3df8019afc7766
2024-07-22 11:28:31 +08:00
hiyouga
dbe26e7cdf tiny fix
Former-commit-id: c333e2f49d23243489fa16622f43f768bcfd45e2
2024-07-22 00:06:03 +08:00
hiyouga
8d06679a3f fix flashattn + packing
Former-commit-id: 4135e69406c09f3892276e4fee7e5757a52a42d6
2024-07-21 17:07:45 +08:00
hiyouga
81fd5097cc update wechat
Former-commit-id: ad71296a7cc04d0c72721de18c52d8d0c2d9ad83
2024-07-20 22:00:44 +08:00
hiyouga
726e7046db set dev version
Former-commit-id: 88c7fc159999511e6e19fff3d37147a6a7064335
2024-07-19 02:01:46 +08:00
hiyouga
542658c986 update parser
Former-commit-id: 8f6995081cbdbb2424da586a443e5220a8990faa
v0.8.3
2024-07-19 01:36:39 +08:00
hiyouga
f5cfea56bd release v0.8.3
Former-commit-id: bbd5a644230d633f507c72929e8819c07ae38bba
2024-07-19 01:21:18 +08:00
hiyouga
488f392c81 fix test
Former-commit-id: cdb0f34f10f5407e83766a8c5c9c5aff6af2a84e
2024-07-19 01:17:37 +08:00
hiyouga
d0891f05fa fix unittest
Former-commit-id: e80006795fe6344ea98b61f9a8db16356498c7cb
2024-07-19 01:10:30 +08:00
hiyouga
e1e01d7efd add unittest
Former-commit-id: 608de799a21f37319bf31c04c0aa50c4542ec757
2024-07-19 01:06:27 +08:00
hiyouga
34f16cc635 follow #4878 fix #4684
Former-commit-id: 779aae83d253de0a86201ff87543b5d695e28d23
2024-07-18 22:06:12 +08:00
hoshi-hiyouga
c8e77c11d1 Merge pull request #4878 from ly863/main
Train the last turing conversation.

Former-commit-id: 2516763d698db480f86e397f437fe9c89a7423e0
2024-07-18 22:03:41 +08:00
Shiyu Zhang
249adacc4d 仅仅训练最后一轮对话
Former-commit-id: 1e7b396ff2489055574fd3365425d26360d73897
2024-07-18 15:30:25 +08:00
hiyouga
3c7b10b1fa fix metrics #4786
Former-commit-id: beec77a0898a39d94f41c23920415f5b4873a23a
2024-07-17 00:47:00 +08:00
hiyouga
e90fae61f4 support batch_eval_metrics, fix #4826
Former-commit-id: d774b94f124923829b2eae428e25199d503ebfcb
2024-07-17 00:33:00 +08:00
hiyouga
ca40e42b3c tiny fix
Former-commit-id: bda302fbfbdb114dee7782d405732600d2d73279
2024-07-15 23:09:50 +08:00
hoshi-hiyouga
9d8e0f0837 Merge pull request #4822 from codemayq/test-ci
add github action check to ignore some test cases

Former-commit-id: f2aaebdbde45018e0d08db853ddb975bc2547e14
2024-07-15 23:07:55 +08:00
hoshi-hiyouga
d63c3be556 Update test_template.py
Former-commit-id: 10289eab158c2de13bdde2d5a7c644195e516201
2024-07-15 23:04:39 +08:00
hoshi-hiyouga
c790997fbc Update test_template.py
Former-commit-id: da990f76b881382b9ae6fcfef78dc7df8034947b
2024-07-15 23:00:27 +08:00
hoshi-hiyouga
b19e2f84b6 Merge pull request #4821 from codemayq/feature-eval-split
add "split" as suffix in eval task name

Former-commit-id: 38bc411d42108e7859ec6a031f63c5188246f18c
2024-07-15 22:59:44 +08:00
hoshi-hiyouga
df1f0a1258 Update llama3_lora_eval.yaml
Former-commit-id: 91ba083f37146da0ee321a75701ae79c527ecb51
2024-07-15 22:55:12 +08:00
hoshi-hiyouga
c0493daa60 Update test_template.py
Former-commit-id: 33420bab81cfc7db1dfd3cd4200b8681bf7de9e6
2024-07-15 22:55:05 +08:00
hoshi-hiyouga
f67ddc05d6 Update test_template.py
Former-commit-id: 52a4256ad9aa866f6e1bcbe2c663c0f8ecfdb604
2024-07-15 22:52:25 +08:00
hiyouga
84e6715423 fix #4820
Former-commit-id: fd8cc490084aba9b5155eaaaf26129efd2871fa3
2024-07-15 22:32:07 +08:00
hiyouga
ae0f4ba2d3 update wechat
Former-commit-id: b0aa321a4ad6f146b5d30de20c07feef59f9d0d0
2024-07-15 22:02:52 +08:00
codingma
7146b9457c add IN_GITHUB_ACTIONS
Former-commit-id: 32c3afdfa18dc9560009b324fdf4f2987fc739a9
2024-07-15 10:28:07 +08:00
codingma
76046dfda8 1. change the task name format
2. delete split param in data_args.py


Former-commit-id: 645211dc01b5d4db3ccd0e3dce03a53860eded26
2024-07-15 09:55:33 +08:00
hiyouga
22859b8734 allow computing rouge in training
Former-commit-id: 99ab7a8c1c966232faa11b6a42b9740d9a20ace3
2024-07-15 01:16:26 +08:00
hiyouga
14bc7b0551 fix up
Former-commit-id: 29ebcd75d55f70f2891632eba187b643cc3a9e51
2024-07-15 01:04:56 +08:00
hoshi-hiyouga
2b22a7da48 Merge pull request #4691 from codemayq/feature-suppot-eval-dataset
add eval dataset support

Former-commit-id: 15b399a82f45b08fc07d2957884fb7821eba9fd9
2024-07-15 01:00:34 +08:00
hoshi-hiyouga
788dc1c679 Update data_args.py
Former-commit-id: cba673f491c5d97aba62aea03f310bd54fb3fe28
2024-07-15 00:56:03 +08:00
hoshi-hiyouga
30a3c6e886 Update preprocess.py
Former-commit-id: df52fb05b1b08887288bbaab7c612b7ac27c2290
2024-07-15 00:55:36 +08:00
hoshi-hiyouga
eed7cbb453 Update parser.py
Former-commit-id: 84e4047f8a1f78256be65f3f7bddce358ed9e882
2024-07-15 00:55:21 +08:00
hoshi-hiyouga
5633c0ab1e Update data_utils.py
Former-commit-id: 97a0e291c79f145950b54a11d03d81ada4784d22
2024-07-15 00:54:34 +08:00
hoshi-hiyouga
2e9c9471da Update loader.py
Former-commit-id: a5b809516e7de1d6d5f4583089fee3028d0db01d
2024-07-15 00:50:06 +08:00
hiyouga
a9a652eb6f update test template
Former-commit-id: a4ae3ab4ab8e3c6ad9feba4c185e3b592eda3f09
2024-07-15 00:49:34 +08:00
hoshi-hiyouga
140b512426 Update parser.py
Former-commit-id: 3d39d74003c4ca36f9c9b77f622d366383b0af7e
2024-07-14 23:04:34 +08:00
hoshi-hiyouga
ddbd848e49 Update README.md
Former-commit-id: 9d64507bd5d47f096e81c90bfb347690afaaec2b
2024-07-14 21:27:04 +08:00
hiyouga
2564269826 add gemma test
Former-commit-id: f1d8d29bc3ba1b41a72a24834a16a3d125d56461
2024-07-14 18:01:45 +08:00
hiyouga
380c7741f5 fix test
Former-commit-id: 173921419dc24506527cf506bfbfc01541fd2b66
2024-07-14 15:44:30 +08:00
hiyouga
dfd2d912cd fix #4699
slow tokenizer for yi models


Former-commit-id: 88a20ba7972c533d650967a118d612471fe2b2e8
2024-07-14 15:34:22 +08:00
hiyouga
12e0e5d0d7 tiny fix
Former-commit-id: d3c01552e0f978f150902175f096f6e3bfb64363
2024-07-14 10:56:45 +08:00
hiyouga
0b26011181 fix gemma2 attention
Former-commit-id: 2f6af73da28c4f8321b625fd09ddec8bd4977b08
2024-07-13 23:33:45 +08:00
hiyouga
fb387ae1c3 update workflows
Former-commit-id: 7b19e99ed73faea99c35d49a611187ba1a5c8c73
2024-07-13 22:31:15 +08:00