Skip to content

Pull requests: modelscope/ms-swift

New pull request New
24 Open 2,556 Closed
24 Open 2,556 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
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[model] qwen3-vl support mixed data
#6161 opened Oct 16, 2025 by Jintao-Huang Loading…
4
Update loss_scale method call to pass through inputs.extra_kwargs
#6160 opened Oct 15, 2025 by CJack812 Loading…
1 of 4 tasks
4
[template] add_retry
#6138 opened Oct 14, 2025 by Jintao-Huang Loading…
9
Add SeedAgentTemplate
#6128 opened Oct 14, 2025 by hpsun1109 Loading…
1 of 4 tasks
10
[WIP] refactor template
#6085 opened Oct 11, 2025 by Jintao-Huang Loading…
4
[bugfix] add tools fileds in inputs2reqeusts
#6054 opened Oct 9, 2025 by hjh0119 Loading…
3
[WIP] Megatron GRPO
#6025 opened Sep 30, 2025 by hjh0119 • Draft
4
[grpo] Optimize vLLM weight synchronization
#5773 opened Sep 11, 2025 by hjh0119 Loading…
13
update docs
#5691 opened Sep 6, 2025 by Jintao-Huang Loading…
2
[model] update minicpmv-4.5 video processor
#5679 opened Sep 5, 2025 by hjh0119 Loading…
2
bug fix: RuntimeError when training GRPO with LoRA and PtEngine
#5645 opened Sep 3, 2025 by chenjianhuii Loading…
1 of 4 tasks
6
Bug fix: eval OOM due to deepcopy of torch model
#5607 opened Aug 29, 2025 by hellopahe Loading…
1 task done
5
[template] fix suffix of ChatML template bug Something isn't working
#5589 opened Aug 28, 2025 by popomen Loading…
1 of 4 tasks
4
[init]support gptq grpo in colocate mode
#5569 opened Aug 27, 2025 by ItGirls Loading…
1 of 4 tasks
15
support ernie_vl stale
#4763 opened Jun 30, 2025 by Jintao-Huang Loading…
Update dataset_info.json stale
#3723 opened Mar 31, 2025 by sandeep-sm Loading…
3 tasks
[WIP] support reasoning_content
#3159 opened Feb 18, 2025 by Jintao-Huang Loading…
loss_scale bug when meeting <image>
#3036 opened Feb 8, 2025 by mangoyuan • Draft
1 of 4 tasks
add example OCRBench dataset
#2677 opened Dec 17, 2024 by ex-yanminmin001 Loading…
3 tasks
support pixtral large
#2481 opened Nov 20, 2024 by Jintao-Huang • Draft
Allow flexibility for users to pass attention_mask in data_collator
#2234 opened Oct 13, 2024 by YerongLi Loading…
3 tasks
5
# 观察数据后，发现下面的代码会过滤掉一些没有问题的数据，如：sure, here are some tools and …
#1931 opened Sep 4, 2024 by KnightLancelot Loading…
4 tasks
add push to hub tracker
#1214 opened Jun 24, 2024 by tastelikefeet Loading…
1 of 4 tasks
Fix bug for less data then grad acc
#779 opened Apr 23, 2024 by Firmament-cyou Loading…
1 of 4 tasks
ProTip! Mix and match filters to narrow down what you’re looking for.