hoshi-hiyouga
7f74e54bee
Merge pull request #6010 from XYZliang/fix-#4316
...
Increase shm_size to 16GB in docker-compose.yml
Former-commit-id: 8e9f4617f2
2024-11-25 00:16:42 +08:00
hoshi-hiyouga
3f3eeedca0
Merge pull request #6125 from hiyouga/hiyouga/fix_cli
...
[cli] remove shell=True in cli
Former-commit-id: 57953c8ff6
2024-11-25 00:07:35 +08:00
hiyouga
65699c29d4
fix vllm
...
Former-commit-id: 13ee1f5cec
2024-11-25 00:07:24 +08:00
hiyouga
a04538e70b
fix cli
...
Former-commit-id: 8792d78c82
2024-11-24 23:56:21 +08:00
hiyouga
708116a5f3
release v0.9.1
...
Former-commit-id: d622f8fdec
2024-11-24 23:48:41 +08:00
hoshi-hiyouga
5a7ff02806
Merge pull request #6123 from hiyouga/hiyouga/fix_qwen2vl_vllm
...
[inference] fix qwen2vl vllm infer
Former-commit-id: 0ce173e2a4
2024-11-24 23:42:11 +08:00
hiyouga
dcc67ac1a5
fix qwen2vl vllm infer
...
Former-commit-id: fa50fc470e
2024-11-24 23:27:24 +08:00
hoshi-hiyouga
7ed5a712f8
Merge pull request #6121 from hiyouga/hiyouga/readme
...
[readme] update readme
Former-commit-id: f2bfa80d55
2024-11-24 03:28:09 +08:00
hiyouga
7eaafe08bc
update readme
...
Former-commit-id: a89ad72d03
2024-11-23 19:27:18 +00:00
hoshi-hiyouga
503327b5bb
Merge pull request #6120 from hiyouga/hiyouga/fix_ci
...
[test] fix ci
Former-commit-id: 5f310d9279
2024-11-24 03:21:11 +08:00
hiyouga
4bba121f43
fix ci
...
Former-commit-id: b52c38350d
2024-11-23 19:13:32 +00:00
hoshi-hiyouga
8dff6f630c
Merge pull request #5555 from marko1616/feat/llama3.2vl
...
Support llama3.2 vision
Former-commit-id: e68ef89600
2024-11-24 02:49:07 +08:00
hiyouga
253752ccca
add forbidden modules
...
Former-commit-id: df477370dc
2024-11-23 18:34:15 +00:00
hiyouga
e99031daa4
fix inputs
...
Former-commit-id: 446441fdb0
2024-11-23 18:26:02 +00:00
marko1616
23fc0c863e
Linter.
...
Former-commit-id: b1e43e56db
2024-11-23 16:09:04 +00:00
marko1616
3295519099
Tiny fix.
...
Former-commit-id: 8372c5e377
2024-11-23 16:09:01 +00:00
marko1616
20faaf3418
Support llama3.2vl.
...
Former-commit-id: 3f2c056253
2024-11-23 16:07:35 +00:00
hoshi-hiyouga
24419dd3f1
Merge commit from fork
...
[patch] Patch remote OS command injection vulnerability
Former-commit-id: b3aa80d54a
2024-11-21 22:39:44 +08:00
hoshi-hiyouga
1eaaa85980
do not split save_cmd ret value
...
Former-commit-id: d20b97e7e9
2024-11-21 22:30:23 +08:00
superboy-zjc
e272f87849
[patch] Patch remote OS command injection vulnerability
...
Former-commit-id: aa6a174d68
2024-11-21 01:52:12 -05:00
hoshi-hiyouga
4d49dc0559
Merge pull request #6098 from hiyouga/hiyouga-patch-2
...
update wechat
Former-commit-id: c8f199881a
2024-11-21 14:26:03 +08:00
hoshi-hiyouga
527ea7297b
update wechat
...
Former-commit-id: acf491fc3a
2024-11-21 14:25:33 +08:00
hoshi-hiyouga
302e4e22bf
Merge pull request #6078 from wtmlon/support-efficient-tokens-calculation
...
support effective tokens calculation on sft/dpo
Former-commit-id: bd639a137e
2024-11-20 13:43:15 +08:00
hoshi-hiyouga
2ea2bc7c71
Merge pull request #6083 from hiyouga/hiyouga-patch
...
[asset] update wechat
Former-commit-id: fdcc78b639
2024-11-20 11:46:54 +08:00
hiyouga
505edd4da0
update wechat
...
Former-commit-id: 2f959c73b5
2024-11-20 10:57:30 +08:00
Ting
e27a0c3d53
code refactor
...
Former-commit-id: 40627c601e
2024-11-19 20:33:18 +08:00
Ting
32656bc50d
update
...
Former-commit-id: f566ecc8d1
2024-11-19 19:12:10 +08:00
Ting
bf2b8df540
update
...
Former-commit-id: ef6e14550d
2024-11-19 19:10:07 +08:00
Ting
7ad5b5c088
support efficient tokens calculation on sft/dpo
...
Former-commit-id: b9f00286d8
2024-11-19 17:15:47 +08:00
hoshi-hiyouga
a2a9936e1f
Merge pull request #6065 from hiyouga/hiyouga-patch-1
...
[misc] fix dep package version
Former-commit-id: 9c0f6556ee
2024-11-18 21:13:59 +08:00
hoshi-hiyouga
618a8e6c9f
fix #6061
...
Former-commit-id: 4ac5b97011
2024-11-18 20:56:44 +08:00
hoshi-hiyouga
acd70faf17
Merge pull request #6052 from hiyouga/hiyouga-patch-1
...
[trainer] fix DPO metrics
Former-commit-id: 45f32916ce
2024-11-16 16:20:12 +08:00
hoshi-hiyouga
9815d1712c
fix #6050
...
Former-commit-id: dc82821872
2024-11-16 16:11:16 +08:00
hoshi-hiyouga
e3a0640659
Merge pull request #6046 from hiyouga/hiyouga/add_code_model
...
[model] add qwen-coder and opencoder
Former-commit-id: 6c0847899d
2024-11-15 21:58:03 +08:00
hiyouga
d4e0010027
add qwen-coder and opencoder
...
Former-commit-id: 431ac4892c
2024-11-15 21:48:38 +08:00
codingma
d6b9a2024b
Merge pull request #6022 from codemayq/main
...
update wechat
Former-commit-id: 8e5aad3ffa
2024-11-14 10:03:46 +08:00
codemayq
625ae6f456
update wechat
...
Former-commit-id: fc1aa8f45c
2024-11-14 10:02:06 +08:00
XYZliang
1c1e48a570
Increase shm_size to 16GB in docker-compose.yml to optimize shared memory allocation for large-scale model fine-tuning tasks.
...
This pull request increases the shm_size parameter in docker-compose.yml to 16GB. The goal is to enhance the LLaMA-Factory framework’s performance for large model fine-tuning tasks by providing sufficient shared memory for efficient data loading and parallel processing.
This PR also addresses the issues discussed in [this comment](https://github.com/hiyouga/LLaMA-Factory/issues/4316#issuecomment-2466270708 ) regarding Shared Memory Limit error.
Former-commit-id: 64414905a3
2024-11-13 10:13:59 +08:00
hoshi-hiyouga
8ae2056b59
Merge pull request #5990 from hiyouga/hiyouga/dev_vllm
...
[generate] fix vllm config args
Former-commit-id: 3eebae892b
2024-11-11 14:10:35 +08:00
hoshi-hiyouga
9c394f11ef
fix #5988
...
Former-commit-id: 8d70edf39b
2024-11-11 13:57:14 +08:00
hoshi-hiyouga
662093b38c
Merge pull request #5984 from hiyouga/hiyouga/wechat
...
[readme] update wechat
Former-commit-id: 2176224f4b
2024-11-10 22:08:55 +08:00
hiyouga
e928f7fc4c
update wechat
...
Former-commit-id: f2a44e1a2a
2024-11-10 22:08:10 +08:00
hoshi-hiyouga
82344629af
Merge pull request #5982 from hiyouga/hiyouga/vllm_args
...
[args] add vllm config
Former-commit-id: 1ca6b1582f
2024-11-10 21:37:18 +08:00
hiyouga
0d18cca0db
add vllm config
...
Former-commit-id: 58ab4579dc
2024-11-10 21:28:18 +08:00
hoshi-hiyouga
0386fa6a4f
Merge pull request #5973 from JJJJerry/fix_vllm_generate
...
fix VllmEngine: 将inputs参数替换为prompt
Former-commit-id: 40a2fcc02d
2024-11-10 21:04:38 +08:00
hoshi-hiyouga
d7476aa55b
Update vllm_engine.py
...
Former-commit-id: a543bc478d
2024-11-10 20:57:00 +08:00
JJJJerry
d996bea1c7
fix VllmEngine: 将inputs参数替换为prompt
...
Former-commit-id: 1d04078bb5
2024-11-09 11:45:59 +08:00
hoshi-hiyouga
1e00de38cb
Merge pull request #5971 from hiyouga/hiyouga/fix_webui
...
[webui] fix extra args
Former-commit-id: adc5849ce7
2024-11-09 00:25:24 +08:00
hiyouga
d7e35ddcaa
fix extra args
...
Former-commit-id: eb294fed13
2024-11-09 00:24:27 +08:00
hoshi-hiyouga
162f7028fc
Merge pull request #5970 from hiyouga/hiyouga/fix_beam
...
[generation] fix vllm v0.6.3
Former-commit-id: 39e330196d
2024-11-08 23:58:15 +08:00
