Does the OLMoE model and its code support customizing the MoE routing mechanism for fine-tuning?
Open
- Dominant language
- Jupyter Notebook
- Stars
- 1.1k
- Forks
- 120
- PR merge metrics
- No merged PRs in 30d
Description
Does the open-sourced OLMoE model and its code support modifying the MoE routing mechanism for fine-tuning? If yes, could you please show me where is the source code located to enable modify the routing mechanism?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.