estrogen / Moonlight-16B-A3B-less-cursed

Text Generation16B200Updated Mar 2, 2025

Downloads

20

Likes

0

Last updated

Mar 2, 2025

License

mit

- Weight Decay: Critical for scaling to larger models - Consistent RMS Updates: Enforcing a consistent root mean square on model updates

Tasks & library

  • text generation
  • transformers

Tags

  • transformers
  • deepseek_v3
  • text-generation
  • conversational
  • custom_code

Technical specifications

Parameters16B
Librarytransformers
LanguagesNot available
Licensemit