modelscope / modelscope/ms-swift
合并sft训练的lora的qwen3-30b-a3b模型报错
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 15.7k
- Forks
- 1.7k
- Avg merge
- 1d 16h
- Merged PRs (30d)
- 136
Description
Checklist / 检查清单
- I have searched existing issues, and this is a new bug report. / 我已经搜索过现有的 issues，确认这是一个新的 bug report。
Bug Description / Bug 描述
ValueError: Target module Qwen3MoeTopKRouter() is not supported. Currently, only the following modules are supported: torch.nn.Linear, torch.nn.Embedding, torch.nn.Conv1d, torch.nn.Conv2d, torch.nn.Conv3d, transformers.pytorch_utils.Conv1D, torch.nn.MultiheadAttention..
How to Reproduce / 如何复现
ValueError: Target module Qwen3MoeTopKRouter() is not supported. Currently, only the following modules are supported: torch.nn.Linear, torch.nn.Embedding, torch.nn.Conv1d, torch.nn.Conv2d, torch.nn.Conv3d, transformers.pytorch_utils.Conv1D, torch.nn.MultiheadAttention..
Additional Information / 补充信息
No response
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the SFT LoRA merge for the Qwen3-30B-A3B model and trace where Qwen3MoeTopKRouter is validated as a target module. The issue provides no file or test entry point, so first identify the relevant PEFT integration path; done means the merge completes without the reported ValueError.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 38/100