Skip to content

Issues: modelscope/ms-swift

GRPO (R1) 训练交流群
#3076 opened Feb 12, 2025 by Jintao-Huang
Open 3
Megatron-SWIFT训练交流群
#3604 opened Mar 21, 2025 by Jintao-Huang
Open
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

473 Open 1,485 Closed
473 Open 1,485 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

【bug】Failed to open local file in cache
#3667 opened Mar 25, 2025 by jdy18
使用GRPO训练llava-1.5以及qwen2-vl时，使用vllm推理，在eval时报错
#3666 opened Mar 25, 2025 by zsxm1998
1
cannot import name 'LoRA' from 'swift'
#3665 opened Mar 25, 2025 by Ethereeall
1
[Bug]: RuntimeError: setup failed!
#3662 opened Mar 25, 2025 by ShuhangChen1207
gemma3使用grpo用vllm的bug
#3660 opened Mar 25, 2025 by moutozf04
1
微调qwen2.5vl grouding
#3659 opened Mar 25, 2025 by 1804696177
1
weighted loss for different class 为不同数据的loss分配不同的权重 enhancement New feature or request
#3654 opened Mar 25, 2025 by Li-Jicheng
Ascend NPU下，GRPO训练时死循环
#3650 opened Mar 25, 2025 by RyanOvO
建议增加稳定版本的安装文档
#3644 opened Mar 25, 2025 by PiggerZZM
1
能推理但是merge完部署后报错无法找到 adapter_config.json
#3643 opened Mar 25, 2025 by wookpeckerjohn
1
二分类任务大模型微调，token_acc表示什么
#3639 opened Mar 25, 2025 by kike-0304
1
推理型大模型多轮对话SFT数据集构造问题请教
#3627 opened Mar 24, 2025 by YihengLiu1996
1
zero3offload deepspeed保存报错“assert param.ds_status == ZeroParamStatus.AVAILABLE, param.ds_summary() ”
#3622 opened Mar 24, 2025 by aleien95
1
OSError: [Errno 39] Directory not empty
#3618 opened Mar 23, 2025 by blackMension
1
qwen2.5vl 多图微调 模型退化
#3617 opened Mar 22, 2025 by SeuZL
8
RTX3090上运行sft-rlhf-grpo微调，报错：torch.distributed.DistBackendError: [3] is setting up NCCL communicator and retrieving ncclUniqueId from [0] via c10d key-value store by key '0', but store->get('0') got error: wait timeout after 1800000ms,
#3612 opened Mar 22, 2025 by winni0
12
设置NPROC_PER_NODE后会直接报错 failed (exitcode: -11) local_rank: 1
#3611 opened Mar 22, 2025 by liujiwen0517
1
训练后的RM模型，支持推理引擎sglang/vllm部署
#3610 opened Mar 22, 2025 by Xu-Chen
grpo 固定seed，结果依旧不可复现
#3607 opened Mar 21, 2025 by gouqi666
SWIFT支持embedding模型的推理和部署如何实现
#3606 opened Mar 21, 2025 by xiaolingzang
Evaluate VLM on RefCoco Dataset
#3605 opened Mar 21, 2025 by HieuPhan33
Megatron-SWIFT训练交流群
#3604 opened Mar 21, 2025 by Jintao-Huang
reward margin enhancement New feature or request
#3603 opened Mar 21, 2025 by aleien95
GRPO算法训练，后期训练时，显存暴增
#3600 opened Mar 21, 2025 by RyanOvO
2
PPO的训练有没有办法定制熵loss？
#3593 opened Mar 20, 2025 by 2043078895
ProTip! What’s not been updated in a month: updated:<2025-02-25.