737 Commits

Author SHA1 Message Date
hiyouga
b97d454ac1 support chatglm3
Former-commit-id: ba82e13bbeed3b262d301196b1860d73f319401d
2023-10-27 19:16:28 +08:00
hiyouga
b38151754d support dataset cache
Former-commit-id: f79ee62eb4a2a4a01cb4e2a6aa2d07158cf8eb59
2023-10-26 21:48:45 +08:00
hiyouga
70ac3d38f6 fix #1287
Former-commit-id: d885aca472c6448bbf9a9e8d16bead92038825e3
2023-10-26 17:49:41 +08:00
hiyouga
4d6d799ff8 fix #1285
Former-commit-id: 2f8fe4439506e844b147fe38b5eb878c5748c31c
2023-10-26 16:34:52 +08:00
hiyouga
12c4a8da46 remove filter in preprocess
Former-commit-id: 9eac08b35fec47129a29c401ca265343f8388ab0
2023-10-23 23:46:02 +08:00
hiyouga
4c9b8530cb update neftune logic
Former-commit-id: bb4f0589ed23bf0236d3e918272ad64f0a05ef39
2023-10-22 17:42:13 +08:00
hiyouga
18059fde78 fix webui
Former-commit-id: a5a5a7bc1f53d36e1b26e418999465903cb7d9ed
2023-10-22 17:24:56 +08:00
hiyouga
78e28c8b8e add new options in webui
Former-commit-id: 6698b832dd9cc2d7d60be4fa5ab90e34a7e9d8e0
2023-10-22 17:17:58 +08:00
hiyouga
c5f28b1496 fix recursion error
Former-commit-id: c7938188c36a71a878bca982b7dd151195164986
2023-10-22 16:28:37 +08:00
hiyouga
31969e78f7 reimplement neftune
Former-commit-id: efe9e5a194d3a9f052701d904715238816e4c09e
2023-10-22 16:15:08 +08:00
hoshi-hiyouga
d66b091087 Merge pull request #1252 from anvie/neftune
add NEFTune optimization

Former-commit-id: 85d5c5fbe731f486c3e83812227fa05edc131487
2023-10-22 15:59:20 +08:00
anvie
202cd43027 add NEFTune optimization
Former-commit-id: 603e0298af64116ac07130fe6661a9ba823c186c
2023-10-21 13:24:10 +07:00
hiyouga
797c3073b3 fix openchat template
Former-commit-id: 88b9b657bc50495ac4c42f64195fc652fe4ca3df
2023-10-21 01:25:42 +08:00
hiyouga
ffa58ecc4d fix tokenizer padding side in evaluate.py
Former-commit-id: bcb43ff8ba1946c1f7e7865c9d0fb47ba276935d
2023-10-21 00:30:04 +08:00
hiyouga
e79f0755a6 fix #1232
Former-commit-id: 49975755d47344e362145c52548fdda8783f2c0c
2023-10-20 23:28:52 +08:00
hiyouga
d460f73e4a fix #1215
Former-commit-id: d91b43a8afbea4859357f2224e3d9b9d71160e6d
2023-10-19 16:19:21 +08:00
hiyouga
35882be86e fix #1218
Former-commit-id: b301f35bd4a3bf368159c8f5fb4e2736f922115b
2023-10-19 16:17:41 +08:00
hiyouga
cd5b2c62ca fix #1228
Former-commit-id: e4e0cae3f55da2f1b566c97dbfdd7fc5b7b728a4
2023-10-19 15:54:10 +08:00
hiyouga
d539e524fa fix #1217
Former-commit-id: 065fc0a6f3f005bb87e1c5c126c8b6bb470ce700
2023-10-19 15:52:24 +08:00
hiyouga
c7518f2c5b rename webui
Former-commit-id: 26feaf80fff6177d9eb4e28ad18feb6d34d3ea27
2023-10-16 15:16:24 +08:00
hiyouga
aac3e56a49 fix #1197
Former-commit-id: 00100e23fcfef9587fda4cf01c62599d996e1176
2023-10-16 15:13:46 +08:00
hoshi-hiyouga
c87267ccd3 Update README_zh.md
Former-commit-id: 3450404bb9a33c3bd4b45ac4afcf51062f8c7d1d
2023-10-16 00:28:27 +08:00
hoshi-hiyouga
83bf791ed1 Update README.md
Former-commit-id: d84896597eded79f78224faed81cc9f2df222978
2023-10-16 00:23:37 +08:00
hiyouga
83033c2ce3 release v0.2.0
Former-commit-id: 7f941c1ab6c52915aa2675fa77cae5efc530fdd9
2023-10-15 20:49:43 +08:00
hiyouga
47245154d1 update readme
Former-commit-id: a99a92b129a3d2372e66ca73b87c3e521f144043
2023-10-15 20:28:14 +08:00
hoshi-hiyouga
49f54a812b Update README.md
Former-commit-id: e6fcc1831dadd2ec2c0acb14697a35f6471139ab
2023-10-15 20:23:22 +08:00
hiyouga
f872297409 fix config, #1191
Former-commit-id: 5dbc9b355e85b203cb43ff72589374f0e04be391
2023-10-15 18:28:45 +08:00
hiyouga
ebe127b7f2 disable tqdm in webui mode
Former-commit-id: 832be571bec2eefb79ea88f110b7827f5c1249e6
2023-10-15 16:18:25 +08:00
hiyouga
cb68572bce refactor export, fix #1190
Former-commit-id: 30e60e37023a7c4a2db033ffec0542efa3d5cdfb
2023-10-15 16:01:48 +08:00
hiyouga
a317943e54 fix eval resuming in webui
Former-commit-id: b28b53cd06777f213ef7b925a914ff5fd357ade1
2023-10-15 15:45:38 +08:00
hiyouga
caf8b3d3b8 tiny fix
Former-commit-id: 47b7b34357708a5354d542ddc239146c6417d718
2023-10-15 05:02:48 +08:00
hiyouga
a0dad14cd2 fix callback
Former-commit-id: 51208655a8c1d66551b7b644247321a3583debdc
2023-10-15 04:59:44 +08:00
hoshi-hiyouga
ef630b60fd Merge pull request #1186 from hiyouga/dev
Support Web UI resuming training

Former-commit-id: fcbecd0c4cb17b883e9b780a71d2abc38228293e
2023-10-15 04:53:14 +08:00
hiyouga
6c835ecb5e implement webui resuming training
Former-commit-id: 2d41672ef52414c56c50c8b4fdc442797ba682e9
2023-10-15 04:52:19 +08:00
hiyouga
fdf5d3ac77 fix bugs in webui
Former-commit-id: 4befa74ea630d90e4d7a1f7d7c34d39257717ec1
2023-10-15 03:41:58 +08:00
hiyouga
66bb8ccb28 refactor webui
Former-commit-id: 813ecd8e51949c21ab6fbaa51cc2b1a84ee07952
2023-10-15 03:06:21 +08:00
hiyouga
8ee069d7c3 fix loading dtype
Former-commit-id: d54a356128f7e335c12089702cf3de7f5b4baf16
2023-10-14 20:15:24 +08:00
hiyouga
0c40610fb5 fix #1176 #1177
Former-commit-id: 5627a2b57c270a78095a32083e2dc7aa02162875
2023-10-14 20:00:17 +08:00
hiyouga
7fea444d48 fix #1184
Former-commit-id: 5b069a967823e659dbc70b0d50361b3ad248087e
2023-10-14 19:20:11 +08:00
hiyouga
08bb6baf76 fix webui
Former-commit-id: a0fe43aac968d9f6ca4724b8d718b45c03063b91
2023-10-13 16:27:59 +08:00
hiyouga
802d9e524e update readme
Former-commit-id: 9d9018fad314cdc4512b4847633489cdd7a25347
2023-10-13 13:53:43 +08:00
hiyouga
0229b4ecf0 update discord link
Former-commit-id: f725cb4940a3a18e9f1edca986ef06d425b39710
2023-10-12 21:44:28 +08:00
hiyouga
c8dfbe280b rename repository
Former-commit-id: 6100ac080a5e52edd66b98147aede6cb77481beb
2023-10-12 21:42:29 +08:00
hiyouga
19582ee70f fix ppo args
Former-commit-id: 0f12899951808f53a482082eb116bda309775930
2023-10-11 23:40:50 +08:00
hiyouga
f1a8fcf917 refactor model_dtype, fix PPO trainer
Former-commit-id: 3e17ee5afbcb823a7c9a2f91864b3750cd79edb4
2023-10-11 23:16:01 +08:00
hiyouga
04008ea0a4 add averaging in evaluation
Former-commit-id: b39d6e0b8658e1c69bbaf6bcb6cfaa8f7af30110
2023-10-10 23:16:31 +08:00
hiyouga
c678dc262d fix aquila template, repair sft packing mechanism
Former-commit-id: 8c82cfa5dd4bec957426b5bf176d242c77552ab0
2023-10-10 18:49:55 +08:00
hiyouga
5bc37ad230 tiny fix
Former-commit-id: 31ccd3329ac634b239c43d60bd955cd95670df16
2023-10-10 17:41:13 +08:00
hiyouga
14cad84211 update readme
Former-commit-id: 4a9c8a4f18b07455c34e6c1e6bbc81cbefd82eea
2023-10-09 20:02:50 +08:00
hiyouga
7bdcd9d507 fix flash shift short attention
Former-commit-id: e44ad23eafa39b3ac0400b6f97cd440106a87f44
2023-10-09 17:54:48 +08:00