deepseek-ai / deepseek-ai/DeepSeek-V2
`V-MoE` token droping and `MoD`
Open
- Dominant language
- No language data
- Stars
- 5k
- Forks
- 550
- PR merge metrics
- No merged PRs in 30d
Description
This token dropping method, as indicated by the citation, is based on the V-MoE method.
How this different from the recent MoD? It look like they very similar techniques.
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.