Circuits-V2
Meridian-Mini
Tags
- pytorch
- mixture-of-experts
- linear-attention
- hybrid-attention
- from-scratch
- research
- en
- de
- ru
- ja
- dataset:HuggingFaceFW/fineweb-edu
- dataset:HuggingFaceTB/finemath
Languages
en, de, ru, ja
- Author
- Circuits-V2
- Task
- text-generation
- License
- mit
- Downloads
- 0
- Likes
- 0