kyy/llm_trainer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
2,409 Commits 1 Branch 0 Tags
3a1402a4ed1fb958cd38903d016b9a87dc85d4cd
Commit Graph
2409 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
hoshi-hiyougaandGitHub 3a1402a4ed Merge pull request #6138 from hiyouga/hiyouga/update_data 
[data] update dataset info
 2024-11-25 21:47:23 +08:00
hoshi-hiyougaandGitHub 5214d3ea06 update dataset 2024-11-25 21:47:04 +08:00
hoshi-hiyougaandGitHub 2b7157dc1d Merge pull request #6137 from hiyouga/hiyouga/fix_mllama 
[model] fix mllama hidden_size
 2024-11-25 20:17:33 +08:00
hoshi-hiyougaandGitHub 75b586c31a fix visual patch 2024-11-25 20:06:06 +08:00
hoshi-hiyougaandGitHub 0516e556a7 fix #6136 2024-11-25 19:43:42 +08:00
hoshi-hiyougaandGitHub 44125da5a5 Merge pull request #6127 from hiyouga/hiyouga/dev_version 
[misc] set dev version
 2024-11-25 01:42:29 +08:00
hiyouga b0ccc2ee86 set dev version 2024-11-25 01:36:49 +08:00
hoshi-hiyougaandGitHub 18daf10eda Merge pull request #6124 from hiyouga/hiyouga/release 
[release] release v0.9.1
 2024-11-25 00:20:02 +08:00
hoshi-hiyougaandGitHub 07059a7ca4 Merge pull request #6126 from hiyouga/hiyouga/fix_vllm 
[inference] fix vllm
 2024-11-25 00:19:54 +08:00
hoshi-hiyougaandGitHub 8e9f4617f2 Merge pull request #6010 from XYZliang/fix-#4316 
Increase shm_size to 16GB in docker-compose.yml
 2024-11-25 00:16:42 +08:00
hoshi-hiyougaandGitHub 57953c8ff6 Merge pull request #6125 from hiyouga/hiyouga/fix_cli 
[cli] remove shell=True in cli
 2024-11-25 00:07:35 +08:00
hiyouga 13ee1f5cec fix vllm 2024-11-25 00:07:24 +08:00
hiyouga 8792d78c82 fix cli 2024-11-24 23:56:21 +08:00
hiyouga d622f8fdec release v0.9.1 2024-11-24 23:48:41 +08:00
hoshi-hiyougaandGitHub 0ce173e2a4 Merge pull request #6123 from hiyouga/hiyouga/fix_qwen2vl_vllm 
[inference] fix qwen2vl vllm infer
 2024-11-24 23:42:11 +08:00
hiyouga fa50fc470e fix qwen2vl vllm infer 2024-11-24 23:27:24 +08:00
hoshi-hiyougaandGitHub f2bfa80d55 Merge pull request #6121 from hiyouga/hiyouga/readme 
[readme] update readme
 2024-11-24 03:28:09 +08:00
hiyouga a89ad72d03 update readme 2024-11-23 19:27:18 +00:00
hoshi-hiyougaandGitHub 5f310d9279 Merge pull request #6120 from hiyouga/hiyouga/fix_ci 
[test] fix ci
 2024-11-24 03:21:11 +08:00
hiyouga b52c38350d fix ci 2024-11-23 19:13:32 +00:00
hoshi-hiyougaandGitHub e68ef89600 Merge pull request #5555 from marko1616/feat/llama3.2vl 
Support llama3.2 vision
 2024-11-24 02:49:07 +08:00
hiyouga df477370dc add forbidden modules 2024-11-23 18:34:15 +00:00
hiyouga 446441fdb0 fix inputs 2024-11-23 18:26:02 +00:00
marko1616andhiyouga b1e43e56db Linter. 2024-11-23 16:09:04 +00:00
marko1616andhiyouga 8372c5e377 Tiny fix. 2024-11-23 16:09:01 +00:00
marko1616andhiyouga 3f2c056253 Support llama3.2vl. 2024-11-23 16:07:35 +00:00
hoshi-hiyougaandGitHub b3aa80d54a Merge commit from fork 
[patch] Patch remote OS command injection vulnerability
 2024-11-21 22:39:44 +08:00
hoshi-hiyougaandGitHub d20b97e7e9 do not split save_cmd ret value 2024-11-21 22:30:23 +08:00
superboy-zjc aa6a174d68 [patch] Patch remote OS command injection vulnerability 2024-11-21 01:52:12 -05:00
hoshi-hiyougaandGitHub c8f199881a Merge pull request #6098 from hiyouga/hiyouga-patch-2 
update wechat
 2024-11-21 14:26:03 +08:00
hoshi-hiyougaandGitHub acf491fc3a update wechat 2024-11-21 14:25:33 +08:00
hoshi-hiyougaandGitHub bd639a137e Merge pull request #6078 from wtmlon/support-efficient-tokens-calculation 
support effective tokens calculation on sft/dpo
 2024-11-20 13:43:15 +08:00
hoshi-hiyougaandGitHub fdcc78b639 Merge pull request #6083 from hiyouga/hiyouga-patch 
[asset] update wechat
 2024-11-20 11:46:54 +08:00
hiyouga 2f959c73b5 update wechat 2024-11-20 10:57:30 +08:00
Ting 40627c601e code refactor 2024-11-19 20:33:18 +08:00
Ting f566ecc8d1 update 2024-11-19 19:12:10 +08:00
Ting ef6e14550d update 2024-11-19 19:10:07 +08:00
Ting b9f00286d8 support efficient tokens calculation on sft/dpo 2024-11-19 17:15:47 +08:00
hoshi-hiyougaandGitHub 9c0f6556ee Merge pull request #6065 from hiyouga/hiyouga-patch-1 
[misc] fix dep package version
 2024-11-18 21:13:59 +08:00
hoshi-hiyougaandGitHub 4ac5b97011 fix #6061 2024-11-18 20:56:44 +08:00
hoshi-hiyougaandGitHub 45f32916ce Merge pull request #6052 from hiyouga/hiyouga-patch-1 
[trainer] fix DPO metrics
 2024-11-16 16:20:12 +08:00
hoshi-hiyougaandGitHub dc82821872 fix #6050 2024-11-16 16:11:16 +08:00
hoshi-hiyougaandGitHub 6c0847899d Merge pull request #6046 from hiyouga/hiyouga/add_code_model 
[model] add qwen-coder and opencoder
 2024-11-15 21:58:03 +08:00
hiyouga 431ac4892c add qwen-coder and opencoder 2024-11-15 21:48:38 +08:00
codingmaandGitHub 8e5aad3ffa Merge pull request #6022 from codemayq/main 
update wechat
 2024-11-14 10:03:46 +08:00
codemayq fc1aa8f45c update wechat 2024-11-14 10:02:06 +08:00
XYZliang 64414905a3 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.
 2024-11-13 10:13:59 +08:00
hoshi-hiyougaandGitHub 3eebae892b Merge pull request #5990 from hiyouga/hiyouga/dev_vllm 
[generate] fix vllm config args
 2024-11-11 14:10:35 +08:00
hoshi-hiyougaandGitHub 8d70edf39b fix #5988 2024-11-11 13:57:14 +08:00
hoshi-hiyougaandGitHub 2176224f4b Merge pull request #5984 from hiyouga/hiyouga/wechat 
[readme] update wechat
 2024-11-10 22:08:55 +08:00