Commit Graph

1470 Commits

Author SHA1 Message Date
hiyouga c450ee87a3 improve KTO impl., replace datasets 2024-05-18 03:44:56 +08:00
hoshi-hiyouga 33a354548e
Merge pull request #3785 from enji-zhou/feature/add_kto
add kto
2024-05-18 03:07:18 +08:00
hoshi-hiyouga d7ff49f245
Merge pull request #3794 from jue-jue-zi/main
feat: pass the `max_lora_rank` parameter to vLLM backend
2024-05-17 16:17:30 +08:00
hoshi-hiyouga 9646727453
Update model_args.py 2024-05-17 16:16:41 +08:00
juejuezi b20d62ba3c feat: pass the `max_lora_rank` parameter to vLLM backend 2024-05-17 16:07:39 +08:00
hiyouga 8af9817605 add deepseek v2 lite model 2024-05-17 13:25:36 +08:00
enji.zhou db1d5a4f51 add kto 2024-05-17 13:09:17 +08:00
hiyouga 84415492bf Update wechat.jpg 2024-05-17 12:18:03 +08:00
hiyouga e5bba7cf1b update badam example #3764 2024-05-17 02:21:10 +08:00
hiyouga d9f190ff1e better dtype handle in loading 2024-05-17 02:14:56 +08:00
hiyouga ddec9e1b84 update examples 2024-05-17 01:02:00 +08:00
hiyouga 694a05fd04 enable inbrowser in webui 2024-05-17 00:08:56 +08:00
hiyouga d77bed4091 add falcon 11b 2024-05-17 00:08:33 +08:00
hiyouga 3df986c679 fix examples #3769 2024-05-16 19:12:09 +08:00
hiyouga 308edbc426 rename package 2024-05-16 18:39:08 +08:00
hiyouga b2fc7aeb03 set dev version 2024-05-16 02:17:31 +08:00
hiyouga 1c910079d8 release v0.7.1 2024-05-16 00:57:16 +08:00
hiyouga 2a67ab3925 fix #3694 2024-05-16 00:35:28 +08:00
hiyouga 44cfa9a1cd fix #3606
https://github.com/huggingface/peft/pull/1706
2024-05-15 23:05:02 +08:00
hiyouga a388cadfc0 add Yi-VL-34B model 2024-05-15 22:58:19 +08:00
hiyouga 73845fcc46 add yi-vl 6b model 2024-05-15 20:02:41 +08:00
hiyouga 51d61fcc89 fix yi vl vllm infer 2024-05-15 19:25:48 +08:00
hiyouga e1f4e53915 add NPU docker images 2024-05-15 19:20:11 +08:00
hoshi-hiyouga 75f405ec30
Merge pull request #3748 from BUAADreamer/main
Add MLLM YI-VL and save processor config during training
2024-05-15 16:40:54 +08:00
hoshi-hiyouga cbeef2aaea
Update visual.py 2024-05-15 16:39:57 +08:00
hiyouga 008e3b3b10 fix fsdp model loading 2024-05-15 16:32:28 +08:00
hoshi-hiyouga 5a0c8a8d34
Update patcher.py 2024-05-15 15:37:07 +08:00
hoshi-hiyouga 780ca8306b
Update template.py 2024-05-15 14:20:39 +08:00
hoshi-hiyouga aa4a8933dd
Update trainer.py 2024-05-15 14:13:26 +08:00
hoshi-hiyouga c309605ff5
Update workflow.py 2024-05-15 14:13:01 +08:00
BUAADreamer db1622f76b rm extra import 2024-05-15 12:48:18 +08:00
BUAADreamer d2bf697400 cast dtype in mm_proj 2024-05-15 11:22:15 +08:00
BUAADreamer 771bed5bde modify style 2024-05-15 10:18:10 +08:00
BUAADreamer 3f4556454c Merge branch 'main' of https://github.com/BUAADreamer/LLaMA-Factory 2024-05-15 09:54:21 +08:00
BUAADreamer 7046144499
Merge branch 'hiyouga:main' into main 2024-05-15 09:54:14 +08:00
BUAADreamer afc6c7b9fd add yivl and save processor to model_dir 2024-05-15 09:54:00 +08:00
hiyouga 11bf282dcc fix bug in vllm engine 2024-05-15 02:17:54 +08:00
hiyouga 144801db09 fix gen args 2024-05-15 01:49:05 +08:00
hiyouga 7e69e71a52 fix examples 2024-05-15 00:26:10 +08:00
hiyouga 5bdad46387 update examples 2024-05-15 00:05:17 +08:00
hiyouga b96d84835f update readme 2024-05-14 23:57:08 +08:00
hiyouga fc547ee591 update readme 2024-05-14 23:55:49 +08:00
hiyouga af343034dd add npu examples 2024-05-14 23:32:53 +08:00
hoshi-hiyouga ee4752f6d2
Merge pull request #3584 from zhou-wjjw/main
Enhancing Ascend 910A Training Efficiency in LlamaFactory with NPU
2024-05-14 22:18:37 +08:00
hiyouga c187b20aaa use robust envs 2024-05-14 21:36:42 +08:00
hoshi-hiyouga 1c3c498902
Update train.py 2024-05-14 20:47:52 +08:00
hoshi-hiyouga 9089bc70c8
Apply suggestions from code review
Co-authored-by: Huazhong Ji <hzji210@gmail.com>
2024-05-14 20:44:21 +08:00
hoshi-hiyouga 0ac6e73f99
Apply suggestions from code review
Co-authored-by: Huazhong Ji <hzji210@gmail.com>
2024-05-14 20:44:04 +08:00
hiyouga cfaee8b4cf fix #3728 2024-05-14 20:37:21 +08:00
BUAADreamer 60b99f80c2
Merge branch 'hiyouga:main' into main 2024-05-14 16:51:38 +08:00