BUAADreamer
|
31259e7e0c
|
support llava-next(video)
|
2024-09-10 12:31:53 +08:00 |
hiyouga
|
bdde35fd2e
|
update accelerate ver for schedule_free optimizers
|
2024-09-09 22:51:08 +08:00 |
|
hiyouga
|
6dc2b00fa2
|
fix mm plugin
|
2024-09-09 22:41:28 +08:00 |
|
hiyouga
|
c93795ae14
|
fix qwen2vl preprocess
|
2024-09-09 22:33:33 +08:00 |
|
hiyouga
|
90d6df6222
|
release v0.9.0 (real)
|
2024-09-09 01:00:25 +08:00 |
|
hiyouga
|
653fe70acb
|
fix constants
|
2024-09-08 23:52:30 +08:00 |
|
hiyouga
|
54b5c4b819
|
release v0.9.0
|
2024-09-08 23:43:35 +08:00 |
|
hiyouga
|
c9b3870adb
|
tiny fix
|
2024-09-08 23:18:08 +08:00 |
|
hiyouga
|
60114179eb
|
update wechat
|
2024-09-08 14:18:12 +08:00 |
|
hiyouga
|
f2aa02c070
|
update scripts
|
2024-09-08 14:17:41 +08:00 |
|
hiyouga
|
b6681d7198
|
support vllm 0.6.0
|
2024-09-08 02:26:20 +08:00 |
|
hiyouga
|
b332908ab4
|
fix test case
|
2024-09-08 01:50:51 +08:00 |
|
hiyouga
|
52a06efaf8
|
add test case
|
2024-09-08 01:40:49 +08:00 |
|
hiyouga
|
fb72a3adb0
|
support activation offloading via unsloth gc
|
2024-09-08 01:22:19 +08:00 |
|
hiyouga
|
54c6905937
|
add docstrings, refactor logger
|
2024-09-08 00:56:56 +08:00 |
hoshi-hiyouga
|
8eac1b929f
|
Merge pull request #5388 from yzoaim/cal_mfu_update
update cal_mfu.py
|
2024-09-08 00:49:28 +08:00 |
|
hoshi-hiyouga
|
842c5455b0
|
fix
|
2024-09-08 00:41:45 +08:00 |
|
hoshi-hiyouga
|
e71133cab1
|
Update cal_mfu.py
|
2024-09-08 00:39:48 +08:00 |
-.-
|
66ec36522c
|
update cal_mfu.py
|
2024-09-07 23:21:35 +08:00 |
|
hoshi-hiyouga
|
36665f3001
|
fix #5384
|
2024-09-07 01:21:14 +08:00 |
|
hiyouga
|
76f2e59504
|
tiny fix
|
2024-09-05 23:41:16 +08:00 |
|
hiyouga
|
eb5aa9adce
|
fix ci
|
2024-09-05 22:39:47 +08:00 |
|
hiyouga
|
2f939b708f
|
fix ci
|
2024-09-05 22:27:48 +08:00 |
|
hiyouga
|
94d5b1bd8f
|
add e2e tests
|
2024-09-05 21:52:28 +08:00 |
|
hoshi-hiyouga
|
1274356263
|
Merge pull request #5372 from LDLINGLINGLING/main
增加了对minicpm3.0的适配'
|
2024-09-05 21:35:42 +08:00 |
liudan
|
3d3fbaaff9
|
根据代码规范修改了代码
|
2024-09-05 20:17:55 +08:00 |
|
hoshi-hiyouga
|
e9bda48c6d
|
fix #5366
|
2024-09-05 18:08:09 +08:00 |
|
hiyouga
|
70e36ff2f4
|
update data readme
|
2024-09-05 04:44:49 +08:00 |
|
hiyouga
|
6055fe02de
|
update data readme
|
2024-09-05 04:25:27 +08:00 |
|
hiyouga
|
359ef8bb0e
|
support Yi-Coder models
|
2024-09-05 03:12:24 +08:00 |
|
hiyouga
|
1173f7fc1d
|
fix ci
|
2024-09-05 03:02:59 +08:00 |
|
hiyouga
|
b6a3fdd056
|
fix ci
|
2024-09-05 02:49:22 +08:00 |
|
hiyouga
|
315284f627
|
update ci
|
2024-09-05 02:26:10 +08:00 |
|
hoshi-hiyouga
|
46b1765d03
|
Merge pull request #5365 from hiyouga/video_finetuning
Support Qwen2-VL Fine-Tuning on Video Datasets
|
2024-09-05 02:24:58 +08:00 |
|
hiyouga
|
c122b9f865
|
tiny fix
|
2024-09-05 02:16:49 +08:00 |
|
hiyouga
|
8cafc7b055
|
video datasets
|
2024-09-05 02:04:17 +08:00 |
|
liudan
|
d7ba97be48
|
增加了对minicpm3.0的适配'
|
2024-09-04 23:10:05 +08:00 |
|
hiyouga
|
c5e1736470
|
fix test
|
2024-09-04 22:38:26 +08:00 |
|
hiyouga
|
dabad5570b
|
update get template
|
2024-09-04 22:36:20 +08:00 |
|
hoshi-hiyouga
|
8f441c2b3a
|
Merge pull request #5323 from naem1023/feat/add-dataset-map-batch-size-argument
Add batch size of map function in the preprocessed dataset
|
2024-09-04 22:09:36 +08:00 |
|
hoshi-hiyouga
|
44d6947e55
|
fix #5228
|
2024-09-04 19:10:30 +08:00 |
|
hiyouga
|
ebddce5d4a
|
fix #5252
|
2024-09-04 03:17:54 +08:00 |
|
hiyouga
|
57497135bf
|
add vl_feedback dataset
|
2024-09-04 03:13:03 +08:00 |
|
hiyouga
|
d41d43a7c3
|
fix #5344
|
2024-09-04 03:06:06 +08:00 |
|
hoshi-hiyouga
|
ce7ed6eb99
|
Merge pull request #5346 from hiyouga/lazy_image
[exp] Lazyload for multimodal inputs
|
2024-09-04 03:00:53 +08:00 |
|
hiyouga
|
47ea97fb1b
|
lazy image load
|
2024-09-04 02:27:08 +08:00 |
|
hiyouga
|
59d2b31e96
|
fix #5334
|
2024-09-03 19:09:42 +08:00 |
|
hiyouga
|
69d0acacc3
|
fix #5338
|
2024-09-03 17:45:17 +08:00 |
|
hiyouga
|
22959bcdd3
|
lint
|
2024-09-03 00:46:25 +08:00 |
|
hiyouga
|
a61c8c4890
|
fix #5324
|
2024-09-02 23:56:21 +08:00 |