Skip to content

Issues: modelscope/ms-swift

GRPO (R1) 训练交流群
#3076 opened Feb 12, 2025 by Jintao-Huang
Open 5
Megatron-SWIFT训练交流群
#3604 opened Mar 21, 2025 by Jintao-Huang
Open 2
ms-swift3 Suggestion Box
#2217 opened Oct 10, 2024 by Jintao-Huang
Open 39
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

537 Open 1,514 Closed
537 Open 1,514 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

How to specify the split (train/validation) for the dataset in cli
#3789 opened Apr 7, 2025 by ma7555
2
regression训练的模型如何部署
#3786 opened Apr 7, 2025 by uRENu
1
gemma3 in grpo doesn't work when using lmdeploy
#3785 opened Apr 7, 2025 by kakao-charlie-cs
1
Ovis2 微调训练成功，使用微调后的模型进行GRPO lora 训练报错 bug Something isn't working
#3784 opened Apr 7, 2025 by Kyrie666
开启断点训练后，为什么剩余时间越来越大了，epoch 和max_steps也和断点训练前接不上呢
#3783 opened Apr 7, 2025 by evyy1234
2
多机多卡swift Colocate训练grpo出现loss在0附近震荡
#3780 opened Apr 7, 2025 by PancakeAwesome
2
train的时候在val_dataset设置多个数据集问题
#3779 opened Apr 7, 2025 by Sakura-not-sleep
1
Use the feature of resume_from_checkpoint when using python code to run finetuning.
#3774 opened Apr 5, 2025 by Jianshu-Hu
1
GRPO训练中间一部分后报错
#3771 opened Apr 5, 2025 by winni0
评测参数bug
#3770 opened Apr 5, 2025 by 1212wuhu
1
GRPO训练报错
#3769 opened Apr 5, 2025 by winni0
Megatron-SWIFT训练导出32B模型显存报错
#3768 opened Apr 4, 2025 by zhangtianhong-1998
4
确保结果的可复现性
#3767 opened Apr 4, 2025 by Sakura-not-sleep
显示HeaderTooLarge
#3764 opened Apr 3, 2025 by lukasindeed
1
grounding微调显示ValueError: remaining_argv: ['--sft_type', 'lora']
#3763 opened Apr 3, 2025 by lukasindeed
1
SFT利用上一次加载数据的缓存
#3762 opened Apr 3, 2025 by Shiki-X
评测时，长度最大只能输出2048，不知道为啥。。。。
#3761 opened Apr 3, 2025 by Kyrie666
Any plans to support megatron for GRPO training?
#3760 opened Apr 3, 2025 by sys-reasoner
评测时，生成参数改了没效果，评测的配置文件还是显示默认参数
#3758 opened Apr 3, 2025 by Kyrie666
1
自定义评测集报错
#3757 opened Apr 3, 2025 by cjl09
1
qwen2.5-omni-7b merge-lora results differ bug Something isn't working
#3756 opened Apr 3, 2025 by vra
ValueError: Cannot use chat template functions because tokenizer.chat_template
#3755 opened Apr 2, 2025 by lqxisok
1
custom data fineturn deepseek-vl-1.3b-chat not work
#3754 opened Apr 2, 2025 by taicr
2
[Question] ImportError when running mPLUG-Owl3-7B with Swift
#3753 opened Apr 2, 2025 by Hubuguilai
2
WeChat Group in Readme 显示群已满
#3752 opened Apr 2, 2025 by JoshonSmith
ProTip! Updated in the last three days: updated:>2025-04-04.