141 Commits

Author SHA1 Message Date
hoshi-hiyouga
222423bcef [breaking] support transformers 4.48 (#6628)
Former-commit-id: f154ab175c513a4d7bb866bf2cffc34b77b50508
2025-01-31 01:36:33 +08:00
yinpu
a8fae3869d fix: avoid redundant normalization in DPO's SFT loss calculation (#6722)
Former-commit-id: 971a8ccbdacf130763d40c7ef82a711b2fc1292f
2025-01-21 13:38:02 +08:00
hoshi-hiyouga
7638f1070e [optim] clean apollo (#6645)
* clean apollo code

* update readme

Former-commit-id: 38b8ec4a99189483124b54df9d6bc6b0d318855a
2025-01-15 01:42:50 +08:00
zhuHQ
c2120432db [optim] add support to APOLLO (#6617)
Former-commit-id: 5a252e5a458457adbd19da3b68a3897ad2962824
2025-01-15 00:24:56 +08:00
hoshi-hiyouga
2a05941b14 [inference] fix stop token for object detection (#6624)
* fix stop token

* update minicpm data pipeline

* fix npu qlora examples

Former-commit-id: 844919fadaa8a61dfae47020971ea80730b2346f
2025-01-13 21:34:20 +08:00
hiyouga
647c51a772 imporve log
Former-commit-id: a6abf375975ffea3d51e1b944c9855b5f62ffac8
2025-01-08 09:56:10 +00:00
hiyouga
0ef1f981da fix llamaboard with ray
Former-commit-id: bd8a432d6a980b1b24a551626304fe3d394b1baf
2025-01-07 09:59:24 +00:00
hiyouga
944a2aec4d refactor ray integration, support save ckpt
Former-commit-id: 2f50b27e608b2092bfceab6c6e84e6631e973ee2
2025-01-07 09:39:10 +00:00
Eric Tang
4f31ad997c run style check
Former-commit-id: 5ec33baf5f95df9fa2afe5523c825d3eda8a076b
2025-01-07 08:55:44 +00:00
Kourosh Hakhamaneshi
8683582300 drafting ray integration
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>

Former-commit-id: 19c12ddae9350f6e25a270fe3372f5b9094cf960
2025-01-07 08:55:44 +00:00
hiyouga
d8bd46f1bf fix #6546
Former-commit-id: 6fcf2f10faf3b1614896b091591eeef96d717e64
2025-01-07 06:30:44 +00:00
hiyouga
2aaf3697d7 fix #6499
Former-commit-id: dffc607220ff6dac15cf501ac9a3cdbe80c25211
2025-01-02 11:28:54 +00:00
hiyouga
f8f05a883b fix #6482
Former-commit-id: 8577f52b4152efe6cc7a8b5f6d37b4f9ba6684e7
2024-12-30 06:03:07 +00:00
hiyouga
88b1874c04 fix #6448
Former-commit-id: 04f78e85af5af14b4c195936623e426a6a128af2
2024-12-27 16:54:39 +00:00
hiyouga
a897d46049 support report custom args
Former-commit-id: d41254c40a1c5cacf9377096adb27efa9bdb79ea
2024-12-21 21:42:45 +00:00
hoshi-hiyouga
0a869c4ed4 Merge pull request #6401 from Zeyi-Lin/hiyouga/swanlab
feat: add swanlab for experiment tracking and visualization.
Former-commit-id: e65fe507f7643bf40b0fc462805c7b7f8ef6b738
2024-12-21 14:09:33 +08:00
ZeYi Lin
8a41c96761 fix: by hiyouga suggestion
Former-commit-id: 41195f1bc69e4b5da7a265369d368b06754362cf
2024-12-20 16:43:03 +08:00
ZeYi Lin
e5d9d8c55d feat: ui improve
Former-commit-id: 6a1effb1741a13ae5238b0e9b429b4cbe3b6534f
2024-12-20 11:03:02 +08:00
ZeYi Lin
925e421bde fix: bugs
Former-commit-id: a2297f97f7587c77d55fbce9ffa81dc60d0b04a1
2024-12-19 21:08:16 +08:00
hiyouga
0385c60177 fix #6391
Former-commit-id: 067ba6e6cb4d8a1d95bba0a108f73008416a2865
2024-12-19 12:16:38 +00:00
ZeYi Lin
44895ebe36 feat: optimize frontend
Former-commit-id: 4a78603c141d9bd78bcaf81261b443cf082bf51f
2024-12-19 19:04:19 +08:00
ZeYi Lin
44dfbf9dbd feat: swanlab params
Former-commit-id: 761b3bdb03e27826fde2ca86d4e37b53c2bbc777
2024-12-19 18:47:27 +08:00
hiyouga
01eeae50b5 support disable shuffling
Former-commit-id: 9d8c35fd6b838ede0bd6827c6c6121f2cba2b11b
2024-12-19 08:53:21 +00:00
hiyouga
7eeeffdb8a add swanlab
Former-commit-id: c85a77c8a8824a56a67d56b97b4877fcd6edeb3d
2024-12-19 07:12:31 +00:00
hiyouga
19ebc0e7a2 support control eos, fix #6345
Former-commit-id: cb0f8399356bf372f3b7963f2565c3d504be0923
2024-12-17 10:42:05 +00:00
hiyouga
aacd9642f5 fix #6348
Former-commit-id: 83e552320909f4775377889f1512994b7e638a7e
2024-12-17 10:06:46 +00:00
hiyouga
fb22651faf fix mrope
Former-commit-id: 55bee1d333549ca19858b3f5c1b7b86926e5fb09
2024-12-12 15:08:17 +00:00
hiyouga
c1768cfb14 support batch infer in vllm
Former-commit-id: 3ef5ed3b9a44eed2f7e3ff221dfc343d0a97c0b5
2024-12-04 13:50:00 +00:00
hoshi-hiyouga
205aca5b03 Merge pull request #6078 from wtmlon/support-efficient-tokens-calculation
support effective tokens calculation on sft/dpo

Former-commit-id: d0510e6d49b43c5ffadd8af653c3bdecc1582417
2024-11-20 13:43:15 +08:00
Ting
87b1f851f1 code refactor
Former-commit-id: ee3f85aa9677d0aeecb3bc396530d2cd7c50dce5
2024-11-19 20:33:18 +08:00
Ting
fca814b30d update
Former-commit-id: 516ed0ea5fed8c74fe3669a7e85dd89b5a0ec3c2
2024-11-19 19:12:10 +08:00
Ting
a20c2b6ecf update
Former-commit-id: a3e8ca53e654136242197a2da872cc0e5cf67880
2024-11-19 19:10:07 +08:00
Ting
fee94e1c54 support efficient tokens calculation on sft/dpo
Former-commit-id: b157d5cccdeb42412b8b440d25d5bdfa8a50be68
2024-11-19 17:15:47 +08:00
hoshi-hiyouga
089e4d9e96 fix #6050
Former-commit-id: 028ea3d9b4fa4ab74a969ac80e61a449d6c15e74
2024-11-16 16:11:16 +08:00
hiyouga
2bb3255e74 fix dpo metrics
Former-commit-id: 57029280da825a39fbf5a05097921b861f126669
2024-11-02 20:59:01 +08:00
hiyouga
093eda2ad6 support rank0 logger
Former-commit-id: 84528eabe560091bfd866b6a0ca864085af7529b
2024-11-02 18:31:04 +08:00
hiyouga
ba66ac084f update tests
Former-commit-id: 4e92b656e324725048d914946e70867be20032ff
2024-11-02 12:41:44 +08:00
hiyouga
8185eb1890 fix incorrect loss value for vlms
Former-commit-id: 0aa29a71ce958343a2086090d647eb63b8f5f5be
2024-10-30 08:56:46 +00:00
hiyouga
43bd1b070c fix #5749
Former-commit-id: c36c5c61fc022b3f144d4c798ec584c4954b0181
2024-10-29 13:02:13 +00:00
hiyouga
22912eba1a fix pissa
Former-commit-id: 4ac65a318b87249d42ffa73cbd3b33f0934f2afa
2024-10-29 12:18:45 +00:00
hiyouga
e2748fa967 fix #5747
Former-commit-id: 26d07de349c98b547cd6a6166ea20616d08ba343
2024-10-29 10:47:04 +00:00
hiyouga
248d5daaff use pre-commit
Former-commit-id: 7cfede95df22a9ff236788f04159b6b16b8d04bb
2024-10-29 09:07:46 +00:00
hoshi-hiyouga
3a8b2890eb fix test
Former-commit-id: a0a23f79d2d94d68e3bf1e90b95beff817bc409c
2024-10-22 12:35:36 +08:00
hiyouga
b2dc6dc59a tiny fix
Former-commit-id: d8ddd07c2ed14d871fb25743c20265fc99e3e221
2024-10-08 17:48:56 +08:00
Chengcheng Pei
26bbfc084d 1, log exceptions in details; 2, check processor is None before calling it.
Former-commit-id: 0f0a4813db9ca4e9bb5762a781a0a214129284a6
2024-09-25 12:59:48 -07:00
hiyouga
7fd0d2fc2f fix #5411
Former-commit-id: 392bdaf1ea9e5baf6289f2d4415a175dd55a479d
2024-09-11 17:36:42 +08:00
hiyouga
dfff411e1a release v0.9.0 (real)
Former-commit-id: 8ff781c8ae5654680f738f69a6db9d7b95d76baf
2024-09-09 01:00:25 +08:00
hiyouga
7f71276ad8 add docstrings, refactor logger
Former-commit-id: c34e489d71f8f539028543ccf8ee92cecedd6276
2024-09-08 00:56:56 +08:00
hoshi-hiyouga
e7f92d16d8 fix #5366
Former-commit-id: b0a4964846dd5be7aa2c54d43f28ba62985587f1
2024-09-05 18:08:09 +08:00
hiyouga
26d914b8fc fix ci
Former-commit-id: 280c0f3f2cea4dfced797cc0e15f72b8b3a93542
2024-09-05 03:02:59 +08:00