Commit Graph

106 Commits

Author SHA1 Message Date
hiyouga
4464a6ff5b tiny fix
Former-commit-id: 451d271718
2024-10-08 17:48:56 +08:00
hoshi-hiyouga
85ed108fa6 Update constants.py
Former-commit-id: 4d7bb69234
2024-09-30 16:47:52 +08:00
shing100
0a633f8098 add Exaone3.0 template
Former-commit-id: 3a9569647f
2024-09-30 09:18:25 +09:00
hoshi-hiyouga
6e4d5d9b2a Update constants.py
Former-commit-id: b257b91cd0
2024-09-29 23:45:34 +08:00
BUAADreamer
b37bb592ec fix constants
Former-commit-id: bec1cb8d55
2024-09-29 22:40:43 +08:00
BUAADreamer
87ab7fc01c fix constants
Former-commit-id: 485fc04716
2024-09-29 22:00:01 +08:00
BUAADreamer
1b71afb277 add more llava-next series template
Former-commit-id: 65a8923f5a
2024-09-29 21:29:29 +08:00
BUAADreamer
5aa1e847d9 add llava-next/llava-next-video/video-llava
Former-commit-id: 6642cd501d
2024-09-28 00:57:03 +08:00
Zhangchi Feng
c576b7ca32 Merge branch 'hiyouga:main' into main
Former-commit-id: 900631755b
2024-09-27 18:14:39 +08:00
hoshi-hiyouga
a73988141b add modelscope models
Former-commit-id: 8e5d12c2c4
2024-09-26 11:22:48 +08:00
marko1616
b70da07977 Chore: Support llama3.2.
Former-commit-id: 885a0b77ab
2024-09-25 16:08:44 -04:00
hoshi-hiyouga
56058e2e84 add qwen2.5 models
Former-commit-id: 92ef62f502
2024-09-19 02:07:54 +08:00
hiyouga
d2f8bcb890 set dev version
Former-commit-id: 0ded765784
2024-09-11 18:56:37 +08:00
Zhangchi Feng
4b6606832c Merge branch 'hiyouga:main' into main
Former-commit-id: 4643089a7d
2024-09-10 13:20:24 +08:00
BUAADreamer
f00f4ae9b6 support llava-next(video)
Former-commit-id: 31259e7e0c
2024-09-10 12:31:53 +08:00
hiyouga
38505ae9e1 update accelerate ver for schedule_free optimizers
Former-commit-id: bdde35fd2e
2024-09-09 22:51:08 +08:00
hiyouga
3aefdad4ec release v0.9.0 (real)
Former-commit-id: 90d6df6222
2024-09-09 01:00:25 +08:00
hiyouga
561ae4d1af fix constants
Former-commit-id: 653fe70acb
2024-09-08 23:52:30 +08:00
hiyouga
fb9280a0a7 release v0.9.0
Former-commit-id: 54b5c4b819
2024-09-08 23:43:35 +08:00
hiyouga
78cf256067 support vllm 0.6.0
Former-commit-id: b6681d7198
2024-09-08 02:26:20 +08:00
hiyouga
7ccb86b215 add docstrings, refactor logger
Former-commit-id: 54c6905937
2024-09-08 00:56:56 +08:00
hoshi-hiyouga
de277a8ab8 Merge pull request #5372 from LDLINGLINGLING/main
增加了对minicpm3.0的适配'

Former-commit-id: 1274356263
2024-09-05 21:35:42 +08:00
liudan
1797fe50a4 根据代码规范修改了代码
Former-commit-id: 3d3fbaaff9
2024-09-05 20:17:55 +08:00
hiyouga
4fccc65579 support Yi-Coder models
Former-commit-id: 359ef8bb0e
2024-09-05 03:12:24 +08:00
hiyouga
9df7a26e6b video datasets
Former-commit-id: 8cafc7b055
2024-09-05 02:04:17 +08:00
liudan
09cff03026 增加了对minicpm3.0的适配'
Former-commit-id: d7ba97be48
2024-09-04 23:10:05 +08:00
hiyouga
cb776752f6 fix mixed mm inputs and rlhf-v
Former-commit-id: 9967ccb3ae
2024-09-01 20:52:47 +08:00
hiyouga
a83756b5e9 refactor mm training
Former-commit-id: 3382317e32
2024-08-30 02:14:31 +08:00
hiyouga
21d3976eea fix #5295
Former-commit-id: ad72f3e065
2024-08-29 20:30:18 +08:00
hiyouga
7b5834b2dd tiny fix
Former-commit-id: f6ae4e75dd
2024-08-27 12:49:32 +08:00
hiyouga
daebca2368 tiny fix
Former-commit-id: c8b4c7fee5
2024-08-20 00:10:52 +08:00
hoshi-hiyouga
5582674f06 Merge pull request #5188 from Zxilly/main
fix: report correct device count for intel xpu
Former-commit-id: d39f4a62d3
2024-08-19 23:51:39 +08:00
Ricardo
a9312387bc _is_bf16_available judgment supports npu
Former-commit-id: 384ab8db84
2024-08-16 02:58:22 +00:00
Zxilly
41a8387195 fix: report correct device count for intel xpu
Former-commit-id: dc36fcc3de
2024-08-15 08:30:43 +00:00
hiyouga
a8add5c04b add qwen2 math models
Former-commit-id: dc770efb14
2024-08-09 20:20:35 +08:00
hiyouga
20013e130b fix #5048
Former-commit-id: b7ca6c8dc1
2024-08-05 23:48:19 +08:00
codingma
7125b6cf70 support gemma-2-2b
Former-commit-id: dc09d454f2
2024-08-01 13:45:48 +08:00
hiyouga
91e54d458f add mistral nemo model
Former-commit-id: 1550fe7331
2024-07-24 16:25:53 +08:00
hiyouga
e0875f82b3 add llama3.1
Former-commit-id: 26533c0604
2024-07-24 16:20:11 +08:00
hiyouga
726e7046db set dev version
Former-commit-id: 88c7fc1599
2024-07-19 02:01:46 +08:00
hiyouga
f5cfea56bd release v0.8.3
Former-commit-id: bbd5a64423
2024-07-19 01:21:18 +08:00
hiyouga
e90fae61f4 support batch_eval_metrics, fix #4826
Former-commit-id: d774b94f12
2024-07-17 00:33:00 +08:00
hoshi-hiyouga
7483e187c6 Update packages.py
Former-commit-id: f84b007ebb
2024-07-07 15:48:29 +08:00
Lian Junhong
7ca84e0a09 chore: Update vllm_engine.py to support vllm version >= 0.5.1
Former-commit-id: 322663bf90
2024-07-07 15:08:12 +08:00
hiyouga
7fcffb860d add codegeex4, internlm2.5
Former-commit-id: 53b1002fb7
2024-07-06 16:16:47 +08:00
hiyouga
7b3c1f29ff fix packing for eager/sdpa attn
Former-commit-id: 6fd6aa4530
2024-07-04 01:52:43 +08:00
hoshi-hiyouga
a38ff842d0 Merge pull request #4224 from chuan298/main
Implement efficient packing without cross-contamination attention

Former-commit-id: 87d9b2d005
2024-07-04 01:18:54 +08:00
hiyouga
bfdaadcc40 update packing
Former-commit-id: cce7083024
2024-07-04 01:10:55 +08:00
hiyouga
e671ed520b update arg name
Former-commit-id: 8a6a7b9c8a
2024-07-03 23:23:24 +08:00
hiyouga
cc31014002 improve rlhf
Former-commit-id: c47ab6c072
2024-07-02 22:23:08 +08:00