147 Commits

Author SHA1 Message Date
hiyouga
3743205c0e add cal_lr.py
Former-commit-id: cea2ba17efc47917e63437a376f220864f7f90dd
2023-11-14 20:58:37 +08:00
hiyouga
088a31ff70 fix #424
Former-commit-id: ca24d445f825e120e659f5cd080a954c2243b8f2
2023-11-13 22:42:23 +08:00
hiyouga
c6dfbfa62c refactor evaluation, upgrade trl to 074
Former-commit-id: ed09ebe2c1926ffdb0520b3866f7fd03a9aed046
2023-11-13 22:20:35 +08:00
hiyouga
d88c72f326 fix flashattn warning
Former-commit-id: 6eb095d39bd82fdbdb729a0ea57fc7246e3a60d6
2023-11-10 18:34:54 +08:00
hiyouga
6a80ba8de4 refactor constants
Former-commit-id: a4d4c3fd35276f20e3b354e9d13ea971029c8775
2023-11-10 14:16:10 +08:00
hiyouga
3e3837f363 tiny fix
Former-commit-id: 97ba2027bb1ddc01a3c824c40d5a180828810c2c
2023-11-09 17:20:49 +08:00
hiyouga
f3c0dbfb26 fix #1452
Former-commit-id: 4d16214467715df458e24d03bb7d303d62b8bdcd
2023-11-09 16:41:32 +08:00
hiyouga
52f33dcdec fix #1438 #1439
Former-commit-id: 84260d58dda22adc32c26bc943ed2a36fd01341d
2023-11-09 13:45:10 +08:00
hiyouga
a3973795a0 fix ppo train and dpo eval
Former-commit-id: ced863031836632cb5920e22ae6991f251372118
2023-11-07 22:48:51 +08:00
hiyouga
cd619fef98 fix #1422
Former-commit-id: 25d7bbd0a5142f001bd2ff498df07b24137050a9
2023-11-07 19:42:01 +08:00
hiyouga
8e1c942844 fix reward model loading
Former-commit-id: 9709ca501180a1afce32e9043aedb359762b437d
2023-11-07 17:20:51 +08:00
hiyouga
940b491609 fix args
Former-commit-id: 44d0fa2ac6a6423c7ddaf91eb8998c1b9248c04e
2023-11-07 16:36:06 +08:00
hiyouga
a5b0251500 update info
Former-commit-id: 89643b8ac1e3fa8d2f29f1c88e4d4503410c0d05
2023-11-07 16:28:21 +08:00
hiyouga
f6df0d2e88 fix #1418
Former-commit-id: 9bfecc72c53cf95fea4a9ff02ec40a65da6d4f54
2023-11-07 16:17:22 +08:00
hiyouga
08df3dca98 upgrade peft, fix #1088 #1411
Former-commit-id: aa7d104f8e050d12cb8f585bc8a52c850995500f
2023-11-07 16:13:36 +08:00
hiyouga
cf413cdd84 update requirements
Former-commit-id: 82ebbbbb80b3f3f616274210970738d0f44b5a0a
2023-11-06 19:01:21 +08:00
hiyouga
412d7aa6b8 fix #1383
Former-commit-id: 9b8a782aa80f27c3e2a2e2621f9be17cae1a27e8
2023-11-06 11:42:23 +08:00
hiyouga
f79d65552c fix #1365
Former-commit-id: 0277d120e62164bb7fa1d6043b8fcc52c881fe96
2023-11-05 12:21:07 +08:00
hiyouga
21fc00f285 tiny fix
Former-commit-id: 594c510a20d6c2782d7b7ffff18931e3003e6c22
2023-11-03 01:26:06 +08:00
hiyouga
3a2a2b902f fix #1290
Former-commit-id: ad911d258c4cea16f54d09bc192e076c21d26394
2023-11-03 00:44:53 +08:00
hiyouga
6bff6a0261 fix bug in data loader, support dpo eval
Former-commit-id: f4f3dcff990468a2fa864b7176adcebbcf16dac9
2023-11-03 00:34:26 +08:00
hiyouga
195ddab8b8 support pagination in webui preview
Former-commit-id: f2307e26b9c2ce5d60917cce5a9638466ea676c8
2023-11-02 21:21:45 +08:00
hiyouga
870e43d2eb fix #1325
Former-commit-id: 59f2cbbd52d4646fbd1ba83032bf522ecc49a50f
2023-11-01 23:38:49 +08:00
hiyouga
0e602345c3 update gradio, support multiple resp in api
Former-commit-id: a34263e7c0e07a080276d164cdab9f12f1d767d2
2023-11-01 23:02:16 +08:00
hiyouga
accfeb5711 fix SFT trainer
Former-commit-id: bf09b6a6cd75cc2738d9af6b8c30bcbba77fa9b5
2023-10-31 21:52:52 +08:00
hiyouga
22abc44236 fix #1316
Former-commit-id: 88a753fe80e277007bac2264aee24024e18f2314
2023-10-31 11:32:08 +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
4c9b8530cb update neftune logic
Former-commit-id: bb4f0589ed23bf0236d3e918272ad64f0a05ef39
2023-10-22 17:42:13 +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
anvie
202cd43027 add NEFTune optimization
Former-commit-id: 603e0298af64116ac07130fe6661a9ba823c186c
2023-10-21 13:24:10 +07:00
hiyouga
35882be86e fix #1218
Former-commit-id: b301f35bd4a3bf368159c8f5fb4e2736f922115b
2023-10-19 16:17:41 +08:00
hiyouga
d539e524fa fix #1217
Former-commit-id: 065fc0a6f3f005bb87e1c5c126c8b6bb470ce700
2023-10-19 15:52:24 +08:00
hiyouga
f872297409 fix config, #1191
Former-commit-id: 5dbc9b355e85b203cb43ff72589374f0e04be391
2023-10-15 18:28:45 +08:00
hiyouga
cb68572bce refactor export, fix #1190
Former-commit-id: 30e60e37023a7c4a2db033ffec0542efa3d5cdfb
2023-10-15 16:01:48 +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
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
0c1e00574d fix shift short attention
Former-commit-id: 9a49cce8e6f6b222f74a07bdab40efee6a77b0f1
2023-10-09 17:07:46 +08:00
hiyouga
b1bc191c45 update webui #1086
Former-commit-id: 65a48bc398f18f71f5f2659b2070e3b9593af243
2023-10-09 14:50:14 +08:00
hiyouga
de8a0d689c fix #1097
Former-commit-id: c5b8796322d9d48e815038f9fecf0ce39036a4ee
2023-10-08 22:29:26 +08:00
hiyouga
536c32d8d4 add llamafy_qwen.py
Former-commit-id: 6cdc91543c022edcc98076488f06e809fde9bad7
2023-10-08 22:05:36 +08:00
hiyouga
4617413bde fix layer norm dtype
Former-commit-id: 67af21961b68d9b54d07b09e444c7140869f26da
2023-09-28 00:25:55 +08:00
hiyouga
d1d5ecb403 fix #1026
Former-commit-id: d0940d0dbd03d4bbcc955304566b0d5507edf9e6
2023-09-27 22:57:09 +08:00
hiyouga
57dafc37cc fix #424
Former-commit-id: daaf89f1126112a73b9f115b0f5617a8cd974a3e
2023-09-27 22:49:43 +08:00
hiyouga
867e513e18 refactor finetuning Args
Former-commit-id: be425a70a4c8f051717cf1e4464dbd79dae4c0b5
2023-09-27 22:28:06 +08:00