ros/LlamaFactory
1
0
Fork 0
mirror of https://github.com/hiyouga/LlamaFactory.git synced 2026-02-01 08:13:38 +00:00
Code Issues Packages Projects Releases Wiki Activity
2,827 Commits 1 Branch 35 Tags
eaf963f67f888acb1aae6e1d2f75358feb54dc5b
Commit Graph

217 Commits

Author SHA1 Message Date
Yaowei Zheng
eaf963f67f [model] update kt code (#9406) 2025-11-05 15:27:22 +08:00
Peilin Li
934b3084ee [train] KTransformers SFT as backend engine for LLaMA-Factory (#9400) 
Co-authored-by: jimmy128 <jimmy128@noreply.gitcode.com>
Co-authored-by: Yaowei Zheng <hiyouga@buaa.edu.cn>
 2025-11-04 15:54:12 +08:00
Yaowei Zheng
3ae15da9c0 [misc] lint code (#9395) 2025-11-03 22:08:59 +08:00
Kingsley
13170577b2 [feat] support megatron-LM training by mcore_adapter (#9237) 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Yaowei Zheng <hiyouga@buaa.edu.cn>
 2025-10-26 16:21:30 +08:00
Yaowei Zheng
d9d67ba62d [misc] fix import error (#9299) 2025-10-17 17:46:27 +08:00
Yaowei Zheng
47a7dc1698 [deps] upgrade vllm (#9293) 2025-10-16 23:20:26 +08:00
Ximing Xing
c867e28093 [model] adds semantic initialization support for special tokens (#9267) 
Co-authored-by: ximingxing <ximingxing@tencent.com>
 2025-10-14 17:00:48 +08:00
Ben Feuer
1c44b60e3e [feat] fp8 training (#8960) 
Co-authored-by: Benjamin Feuer <penfever@gmail.com>
Co-authored-by: Yaowei Zheng <hiyouga@buaa.edu.cn>
 2025-10-01 14:32:53 +08:00
Yaowei Zheng
6ffebe5ff7 [data] fix qwen omni plugin (#9204) 
Co-authored-by: kingsley <kingsleydodonow@gmail.com>
 2025-09-28 01:02:29 +08:00
Yaowei Zheng
2c31279316 [assets] update wechat (#8962) 2025-08-19 02:55:09 +08:00
Zeju Qiu
003a2acb1a [feature] adding orthogononal finetuning (OFT) to llama factory (#8623) 
Co-authored-by: Zeju <zqiu@g003.internal.cluster.is.localnet>
Co-authored-by: Zeju <zqiu@login2.is.localnet>
Co-authored-by: Yaowei Zheng <hiyouga@buaa.edu.cn>
 2025-08-18 18:22:47 +08:00
XLXW
1ada15981a [feature] add support for dft loss (#8917) 2025-08-15 23:29:57 +08:00
Kingsley
936f4fd78e [feature] Support MPO (#8930) 2025-08-15 15:09:59 +08:00
Yaowei Zheng
e695fdfa70 [model] add qwen3 nothink (#8869) 2025-08-11 23:17:32 +08:00
Yaowei Zheng
dc61e78e77 [hparams] fix data args (#8863) 2025-08-08 15:35:50 +08:00
kahlun
8a5d6c8a74 [data-loader] Allow dataset_dir to accept a dict for in-memory dataset_info (#8845) 2025-08-07 16:26:59 +08:00
Yaowei Zheng
a416ab48d8 [deps] upgrade vllm to 0.10.0 (#8787) 2025-07-30 22:26:38 +08:00
Yaowei Zheng
4b0ec83928 [deps] bump transformers to 4.49.0 (#8564) 2025-07-07 20:31:50 +08:00
Ze-Yi LIN
16f13d304b [tracking] fix swanlab hparams (#8532) 
Co-authored-by: Yaowei Zheng <hiyouga@buaa.edu.cn>
 2025-07-02 22:08:44 +08:00
Kingsley
bede213da7 [assets] update readme (#8519) 2025-07-02 15:38:38 +08:00
Injae Ryou
a5a93597b1 [parser] update config loading to use OmegaConf #7793 (#8505) 2025-07-01 21:05:13 +08:00
Yaowei Zheng
c6c764388c [assets] update readme (#8396) 2025-06-17 16:15:20 +08:00
Yaowei Zheng
3a3bae1cfe [data] fix qwen2vl pos ids (#8387) 2025-06-17 00:48:54 +08:00
Yaowei Zheng
9a2d1dec62 [assets] update wechat (#8385) 2025-06-16 18:23:22 +08:00
Aman Gupta
8e4ac78607 [trainer] Add LD-DPO objective (#8362) 2025-06-12 16:10:38 +08:00
hoshi-hiyouga
2bf8e993ab [data] fix shared file system (#8179) 2025-05-27 18:36:03 +08:00
hoshi-hiyouga
9ae17cd173 [deps] update to transformers 4.52 (#8125) 2025-05-21 05:16:18 +08:00
hoshi-hiyouga
9b5baa97f0 [data] qwen3 fixes (#8109) 2025-05-20 02:00:30 +08:00
hoshi-hiyouga
45030ff803 [model] switch to gptqmodel (#8108) 2025-05-19 22:25:40 +08:00
Saiya
ab41f7956c [infer] support lora adapter for SGLang backend (#8067) 2025-05-16 23:33:47 +08:00
hoshi-hiyouga
13b05e74f1 [hparam] add enable think argument (#7928) 2025-04-30 17:21:30 +08:00
hoshi-hiyouga
73198a6645 [misc] fix uv (#7913) 2025-04-30 07:45:03 +08:00
hoshi-hiyouga
d4ee44bdef [data] add eval_on_each_dataset arg (#7912) 2025-04-30 06:56:43 +08:00
Eric Tang
ef03832cd4 [ray] add storage filesystem to ray config (#7854) 2025-04-27 22:12:40 +08:00
Kingsley
fa0eb91f1f [data] fix internvl plugin (#7817) 2025-04-23 00:58:22 +08:00
hoshi-hiyouga
fddcd43c88 [trainer] support early stop (#7797) 2025-04-22 01:59:33 +08:00
hoshi-hiyouga
b07628dea5 [example] add bash usage (#7794) 2025-04-22 00:25:51 +08:00
Juanxi Tian
12ada72ed4 [trainer] Add Muon Optimizer (#7749) 
Co-authored-by: hoshi-hiyouga <hiyouga@buaa.edu.cn>
 2025-04-21 23:38:37 +08:00
hoshi-hiyouga
416853dd25 [parser] support omegaconf (#7793) 2025-04-21 23:30:30 +08:00
flashJd
0ac641326b [misc] fix new tokens adding (#7253) 
Co-authored-by: hoshi-hiyouga <hiyouga@buaa.edu.cn>
 2025-04-21 23:19:02 +08:00
hoshi-hiyouga
d222f63cb7 [infer] set env for vllm ascend (#7745) 2025-04-17 01:08:55 +08:00
hoshi-hiyouga
3df021d4d7 [deps] upgrade vllm (#7728) 2025-04-15 14:57:40 +08:00
hoshi-hiyouga
7c61b35106 [misc] upgrade cli (#7714) 2025-04-14 15:41:22 +08:00
Eric Tang
bb8d79bae2 [ray] allow for specifying ray.init kwargs (i.e. runtime_env) (#7647) 
* ray init kwargs

* Update trainer_utils.py

* fix ray args

---------

Co-authored-by: hoshi-hiyouga <hiyouga@buaa.edu.cn>
 2025-04-10 11:31:05 +08:00
hoshi-hiyouga
c3c0efbaa0 [misc] fix packing and eval plot (#7623) 2025-04-07 18:20:57 +08:00
hoshi-hiyouga
5e22597ff1 [infer] vllm video/audio inference (#7566) 2025-04-02 02:27:04 +08:00
hoshi-hiyouga
2bfcad2394 [model] fix kv cache (#7564) 2025-04-01 23:07:46 +08:00
Billy Cao
00409ff28a [data] shard the dataset to allow multiprocessing when streaming is enabled (#7530) 
* Shard the dataset when streaming to allow multiprocessing

* Allow user to not set dataset_shards to ensure backward compatibility
 2025-04-01 15:36:23 +08:00
Kingsley
7eed496336 [model] add Qwen2.5-Omni model (#7537) 
* preserve image_sizes

* preserve image_sizes

* init plugin

* support audio-text2text lora

* nit

* support image/video-text2text, audio-text2text

* remove args

* remove lines

* add docs && nit

* remove some comments

* fix && add merge part script

* add license
 2025-03-31 20:39:35 +08:00
Xu-pixel
b578a7d5b6 [3rdparty] support swanlab lark notification (#7481) 2025-03-27 01:52:01 +08:00