OpenEuroLLM / OpenEuroLLM/Taskboard
[MoE] z-loss, shared experts and aux loss grid
Open
@swag2198 is already working on this.
Since Jul 28, 2026.
T4.2 - model exploration
- Dominant language
- No language data
- Stars
- 3
- Forks
- 0
- PR merge metrics
- No merged PRs in 30d
Description
Goal
Need to assess the impact of increasing z-loss strength and/or using shared experts on sparse scaling configs.
Description
We choose the 0.4B_ne config with 4/32 experts.
Deliverable scope
- validation loss comparison
- router stability
Dependencies
- compute
Contributor guide
No contributing guide indexed for this repository
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.
Assessment
This issue has not been assessed yet.