Skip to content

Issues: modelscope/ms-swift

Beta
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

630 Open 1,604 Closed
630 Open 1,604 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 run using vllm
#4068 opened May 3, 2025 by weiwei1206
inference error with vllm 0.8.5 bug Something isn't working
#4063 opened May 1, 2025 by zhwk031554
Too many dataloader workers
#4061 opened May 1, 2025 by hertz-pj
1
用grpo训练qwen2.5-7b-instruct出现!!!!
#4060 opened May 1, 2025 by zhangansen
raise KeyError(f"Column {key} not in the dataset. Current columns in the dataset: {columns}") [rank1]: KeyError: 'Column length not in the dataset. Current columns in the dataset: []'
#4058 opened May 1, 2025 by noahwei682
2
The expanded size of the tensor (8) must match the existing size (5) at non-singleton dimension 0.
#4056 opened Apr 30, 2025 by jdy18
1
Qwen3-8B-Base SFT 全参微调保存第一个模型后hang住
#4053 opened Apr 30, 2025 by leileilin
2
transformer_engine 安装失败
#4051 opened Apr 30, 2025 by zhangtianhong-1998
7
dapo时在UserWarning: None of the inputs have requires_grad=True. Gradients will be None一直卡住，直至timeout
#4050 opened Apr 30, 2025 by evyy1234
1
dapo时在UserWarning: None of the inputs have requires_grad=True. Gradients will be None一直卡住，直至timeout duplicate This issue or pull request already exists
#4049 opened Apr 30, 2025 by evyy1234
DPO训练有支持长度惩罚的参数可选吗？
#4048 opened Apr 30, 2025 by leileilin
Add run_name argument support for wandb integration enhancement New feature or request
#4046 opened Apr 30, 2025 by firefighter-eric
[HELP]推理奖励模型报错，感谢大家，求教qwen基座rm后的模型如何vllm推理
#4045 opened Apr 30, 2025 by EvilCalf
3
请求增加一个用于将通过ms-swift微调后的模型转为GGUF格式文件的Notebook文件
#4042 opened Apr 29, 2025 by NianBroken
3
如何将微调成功后的模型转为GGUF格式
#4040 opened Apr 29, 2025 by NianBroken
2
qwen3如何不使用思维链微调
#4038 opened Apr 29, 2025 by zzhiyun
1
不支持bf16报错
#4036 opened Apr 29, 2025 by jfy1016
1
请求增加对Qwen3-8B的自我认知训练的NoteBook文件
#4034 opened Apr 29, 2025 by NianBroken
1
Resumming from checkpoint failed
#4033 opened Apr 29, 2025 by LuckyDoggy
1
🚀 Best Practices for Training Qwen3/Qwen3-MoE good first issue Good for newcomers
#4030 opened Apr 28, 2025 by Jintao-Huang
30
qwen2_5VL missing apply_liger_kernel
#4028 opened Apr 28, 2025 by WeihongM
About the smart_resize of qwen2.5-vl
#4027 opened Apr 28, 2025 by RobinHan24
1
3.4.0版本的swift会过滤数据集，是什么因素导致？
#4026 opened Apr 28, 2025 by llp1992
3
请问有支持步骤奖励的rl方法么
#4024 opened Apr 28, 2025 by EvilCalf
qwen2.5-vl-72b, vllm_server_host方式运行，CUDA out of memory enhancement New feature or request
#4023 opened Apr 28, 2025 by quentin-wang
@hjh0119
3
ProTip! Updated in the last three days: updated:>2025-04-29.