kyy/llm_trainer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
2,350 Commits 1 Branch 0 Tags
8f3a32286ebcfb3234e3981db2292dd165b1568d
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
hoshi-hiyougaandGitHub 707ff5a370 Merge pull request #5929 from hiyouga/hiyouga/dev_wechat 
[readme] update wechat
 2024-11-04 16:44:31 +08:00
hiyouga 882635cac3 update wechat 2024-11-04 08:43:21 +00:00
hoshi-hiyougaandGitHub bcbd1bebb0 Merge pull request #5927 from hiyouga/hiyouga/dev_fixmmchat 
[fix] chat engines
 2024-11-04 16:36:23 +08:00
hiyouga ffa39ba3db add image input type 2024-11-04 08:27:20 +00:00
hiyouga 8c88065c38 fix chat engines 2024-11-04 08:18:12 +00:00
hoshi-hiyougaandGitHub 22ee197a40 Merge pull request #5926 from hiyouga/hiyouga/dev_deps 
[version] update datasets version
 2024-11-04 16:04:00 +08:00
hiyouga c5fae465ec update datasets version 2024-11-04 07:52:26 +00:00
hoshi-hiyougaandGitHub 04c10d2e80 Merge pull request #5914 from hiyouga/hiyouga/dev_read 
[misc] update readme
 2024-11-02 21:44:10 +08:00
hoshi-hiyougaandGitHub 9a42c5f76f Merge pull request #5475 from menibrief/main 
Fix phi-3-small issues
 2024-11-02 21:31:34 +08:00
hoshi-hiyougaandGitHub 478cbb1aa7 update template 2024-11-02 21:21:22 +08:00
hoshi-hiyougaandGitHub 5f14910910 Merge branch 'main' into main 2024-11-02 21:20:27 +08:00
hoshi-hiyougaandGitHub 344ff76d26 Merge pull request #5913 from hiyouga/hiyouga/dev_metrics 
[train] support gather DPO metrics, fix return output
 2024-11-02 21:13:43 +08:00
hoshi-hiyougaandGitHub 07e5088851 Merge pull request #5880 from sd3ntato/make-image-parametric 
make base image parametric.
 2024-11-02 20:26:14 +08:00
hoshi-hiyougaandGitHub 5e8a619d1d Update Dockerfile 2024-11-02 20:20:26 +08:00
hoshi-hiyougaandGitHub c58cc22d06 Merge pull request #5910 from Cuiyn/index 
Support Index series models.
 2024-11-02 20:16:54 +08:00
hoshi-hiyougaandGitHub 83535bbe8b Merge pull request #5912 from hiyouga/hiyouga/dev_logging 
[misc] support rank0 logger
 2024-11-02 18:48:41 +08:00
hoshi-hiyougaandGitHub bd08b8c441 Merge pull request #5909 from hiyouga/hiyouga/dev2 
[data] support auto convert for single image, add image_dir argument
 2024-11-02 13:43:04 +08:00
hoshi-hiyougaandGitHub 8408339d83 Merge pull request #5907 from hiyouga/hiyouga/dev 
[data] fix template replace behavior
 2024-11-02 13:42:53 +08:00
hoshi-hiyougaandGitHub 3ef7d590b1 Merge pull request #5906 from hiyouga/dev 
[test] update tests
 2024-11-02 12:50:43 +08:00
hoshi-hiyougaandGitHub 0a55e60693 Merge pull request #5895 from hiyouga/dev 
[inference] support multiple images
 2024-11-01 16:52:55 +08:00
hiyouga e824b715ad add examples 2024-11-01 08:41:54 +00:00
hiyouga e80a481927 support multiimage inference 2024-11-01 07:25:20 +00:00
hoshi-hiyougaandGitHub 641d0dab08 Merge pull request #5873 from hiyouga/dev 
[misc] update readme
 2024-10-30 17:14:44 +08:00
hiyouga 2417b70a62 update readme 2024-10-30 09:14:01 +00:00
hoshi-hiyougaandGitHub b2d4b9a7a8 Merge pull request #5871 from hiyouga/dev 
[loss&ui] fix incorrect loss of vlms, add extra args to ui
 2024-10-30 17:13:17 +08:00
hiyouga 30567a1487 fix incorrect loss value for vlms 2024-10-30 08:56:46 +00:00
hiyouga 0c22da4f1c tiny fix 2024-10-30 08:56:29 +00:00
hiyouga 86e5affc0d support extra args in llamaboard 2024-10-30 08:55:54 +00:00
hoshi-hiyougaandGitHub 9009a467e6 Merge pull request #5581 from Kuangdd01/pixtral-patch 
[WIP] Support Pixtral-12B
 2024-10-29 22:29:10 +08:00
hoshi-hiyougaandGitHub bb0afda8fb fix bug 2024-10-29 22:19:04 +08:00
hoshi-hiyougaandGitHub 049c554aee Update mm_plugin.py 2024-10-29 22:16:22 +08:00
hoshi-hiyougaandGitHub c3239ba6b2 Update template.py 2024-10-29 22:11:21 +08:00
hoshi-hiyougaandGitHub 0baa7735f6 Update visual.py 2024-10-29 22:10:29 +08:00
hoshi-hiyougaandGitHub f745c4b28f Update collator.py 2024-10-29 22:03:42 +08:00
hoshi-hiyougaandGitHub 6e212fdab5 Update hf_engine.py 2024-10-29 22:00:59 +08:00
hoshi-hiyougaandGitHub 8fa20bf427 Update README_zh.md 2024-10-29 21:58:03 +08:00
hoshi-hiyougaandGitHub 1b57df074a Update README.md 2024-10-29 21:57:28 +08:00
hoshi-hiyougaandGitHub 4ff6e564f8 Merge pull request #5801 from NLPJCL/main 
使用了 LLaMA Factory 的项目：RAG-Retrieval 使用LLaMA-Factory作为生成方法做Reranker任务的微调框架。
 2024-10-29 21:20:16 +08:00
hoshi-hiyougaandGitHub 08d9a03c30 Update README_zh.md 2024-10-29 21:19:17 +08:00
hoshi-hiyougaandGitHub a76478c127 Update README.md 2024-10-29 21:18:15 +08:00
hoshi-hiyougaandGitHub a7c79d8f6a Merge pull request #5857 from hiyouga/dev 
[train] fix saving processor
 2024-10-29 21:12:04 +08:00
hiyouga 23dbe9a099 fix #5749 2024-10-29 13:02:13 +00:00
hoshi-hiyougaandGitHub 935adaeed9 Merge pull request #5852 from hiyouga/dev 
[misc] several important updates
 2024-10-29 20:30:02 +08:00
hiyouga 51e5f96247 fix pissa 2024-10-29 12:18:45 +00:00
hiyouga ae045c884f fix #5747 2024-10-29 10:47:04 +00:00
hiyouga 21db8ed2f4 use pre-commit 2024-10-29 09:07:46 +00:00
hiyouga 77666bd227 update requires 2024-10-29 16:10:07 +08:00
hiyouga 8723922923 update wechat 2024-10-29 15:46:10 +08:00
hoshi-hiyougaandGitHub b4c7dd3ac5 fix #5797 2024-10-23 20:49:44 +08:00
hoshi-hiyougaandGitHub 74a79cc059 fix test 2024-10-22 12:35:36 +08:00
hoshi-hiyougaandGitHub d155b7008c fix #5768 2024-10-22 11:06:22 +08:00
hoshi-hiyougaandGitHub 769fbb6349 Update misc.py 2024-10-17 19:48:51 +08:00
hoshi-hiyougaandGitHub 93b9067dfc Update loader.py 2024-10-17 19:48:12 +08:00
hoshi-hiyougaandGitHub 110e4c548d Update README_zh.md 2024-10-17 19:47:33 +08:00
hoshi-hiyougaandGitHub 1fea871835 Update README.md 2024-10-17 19:46:36 +08:00
hoshi-hiyougaandGitHub 228dd1739e Merge pull request #5665 from johnnynunez/main 
vllm 0.6.3
 2024-10-11 23:45:58 +08:00
hoshi-hiyougaandGitHub bc80ea9a51 Merge pull request #5642 from huniu20/main 
[hub support] add modelers hub support
 2024-10-11 23:45:17 +08:00
hoshi-hiyougaandGitHub f8a2cc6105 Merge pull request #5546 from chengchengpei/cpei/refactor 
1, log exceptions in details; 2, check processor is None before calling it
 2024-10-08 17:46:54 +08:00
hoshi-hiyougaandGitHub 2c6262c3cd Merge branch 'main' into cpei/refactor 2024-10-08 17:31:17 +08:00
hoshi-hiyougaandGitHub 89ba4513ae Merge pull request #5615 from johnnynunez/patch-1 
Update setup.py (Compatible with Jetson)
 2024-10-07 16:50:34 +08:00
hoshi-hiyougaandGitHub 1ce0b42b1e Update parser.py 2024-10-07 16:27:23 +08:00
hoshi-hiyougaandGitHub c2e947de28 Update setup.py 2024-10-07 16:26:50 +08:00
hoshi-hiyougaandGitHub ef84aaceec Merge pull request #5585 from shing100/main 
Support EXAONE3.0 Model
 2024-09-30 16:56:08 +08:00
hoshi-hiyougaandGitHub 4d7bb69234 Update constants.py 2024-09-30 16:47:52 +08:00
hoshi-hiyougaandGitHub 02957fc9c3 Update template.py 2024-09-30 16:39:48 +08:00
hoshi-hiyougaandGitHub c7b334e698 Merge pull request #5574 from BUAADreamer/main 
support llava-next(video)/video-llava
 2024-09-30 00:22:43 +08:00
hoshi-hiyougaandGitHub 2c17d91bb7 Update common.py 2024-09-29 23:58:09 +08:00
hoshi-hiyougaandGitHub e472f355f2 Update README_zh.md 2024-09-29 23:56:32 +08:00
hoshi-hiyougaandGitHub 63148e7271 Update README.md 2024-09-29 23:55:55 +08:00
hoshi-hiyougaandGitHub 2d37fa1255 Update README.md 2024-09-29 23:55:21 +08:00
hoshi-hiyougaandGitHub b257b91cd0 Update constants.py 2024-09-29 23:45:34 +08:00
hoshi-hiyougaandGitHub 8b50ce516a Update test_mm_plugin.py 2024-09-29 22:59:47 +08:00
hoshi-hiyougaandGitHub 905b7c03ae Update requirements.txt 2024-09-29 21:51:23 +08:00
hoshi-hiyougaandGitHub ffaea305fc Update mm_plugin.py 2024-09-29 20:54:04 +08:00
hoshi-hiyougaandGitHub 0257a67cb2 Update mm_plugin.py 2024-09-29 20:53:34 +08:00
hoshi-hiyouga a2bd6944cd update readme 2024-09-29 05:02:44 +00:00
hoshi-hiyougaandGitHub 5ec161d6bd Merge pull request #5580 from amrear/main 
made a small change to a warning about fa2 for gemma2 models.
 2024-09-29 12:45:03 +08:00
hoshi-hiyougaandGitHub fe7057a8a3 Update attention.py 2024-09-29 10:47:41 +08:00
hoshi-hiyougaandGitHub 6b62550af1 Merge pull request #5547 from marko1616/chore/llama3.2 
Chore: Support llama3.2.
 2024-09-26 11:38:34 +08:00
hoshi-hiyougaandGitHub 8e5d12c2c4 add modelscope models 2024-09-26 11:22:48 +08:00
hoshi-hiyougaandGitHub e7f6a9a925 Merge pull request #5533 from StrangeBytesOrg/add-docker-args 
Add additional install options to Dockerfiles
 2024-09-25 23:04:57 +08:00
hoshi-hiyougaandGitHub af8dfb58fd Merge pull request #5483 from whybeyoung/main 
fix: 修复function call数据集如果 function_call 值的为不合法json，异常提示且中断训练。
 2024-09-19 17:01:52 +08:00
hoshi-hiyougaandGitHub f230130563 flat string 2024-09-19 16:43:42 +08:00
hoshi-hiyougaandGitHub af7f547ecb lint 2024-09-19 16:21:43 +08:00
hoshi-hiyougaandGitHub 98b464d2dd fix bug 2024-09-19 16:21:21 +08:00
hoshi-hiyougaandGitHub 36611d5c09 improve error message 2024-09-19 16:06:00 +08:00
hoshi-hiyougaandGitHub ed7d373915 tiny fix 2024-09-19 02:20:24 +08:00
hoshi-hiyougaandGitHub 485d6f8772 Update README_zh.md 2024-09-19 02:17:59 +08:00
hoshi-hiyougaandGitHub cb2cebcd72 Update README.md 2024-09-19 02:16:16 +08:00
hoshi-hiyougaandGitHub f0b930d94a fix webui 2024-09-19 02:13:39 +08:00
hoshi-hiyougaandGitHub 92ef62f502 add qwen2.5 models 2024-09-19 02:07:54 +08:00
hoshi-hiyougaandGitHub 1a3e6545b2 Merge pull request #5438 from aliencaocao/patch-1 
Add qwen_vl to liger kernel supported list
 2024-09-16 13:40:02 +08:00
hoshi-hiyougaandGitHub a76617728a Merge pull request #5427 from HardAndHeavy/update-rocm 
Update the ROCm version to 6.2
 2024-09-13 10:25:47 +08:00
hoshi-hiyougaandGitHub 8eac1b929f Merge pull request #5388 from yzoaim/cal_mfu_update 
update cal_mfu.py
 2024-09-08 00:49:28 +08:00
hoshi-hiyougaandGitHub 842c5455b0 fix 2024-09-08 00:41:45 +08:00
hoshi-hiyougaandGitHub e71133cab1 Update cal_mfu.py 2024-09-08 00:39:48 +08:00
hoshi-hiyougaandGitHub 36665f3001 fix #5384 2024-09-07 01:21:14 +08:00
hoshi-hiyougaandGitHub 1274356263 Merge pull request #5372 from LDLINGLINGLING/main 
增加了对minicpm3.0的适配'
 2024-09-05 21:35:42 +08:00
hoshi-hiyougaandGitHub e9bda48c6d fix #5366 2024-09-05 18:08:09 +08:00
hoshi-hiyougaandGitHub 46b1765d03 Merge pull request #5365 from hiyouga/video_finetuning 
Support Qwen2-VL Fine-Tuning on Video Datasets
 2024-09-05 02:24:58 +08:00