DeepSeek-V2-Lite
Last week, the release and buzz around DeepSeek-V2 have ignited widespread interest in MLA (Multi-head Latent Attention)! Many in the community suggested open-sourcing a smaller MoE model for in-depth research.
text → text · made by deepseek-ai
Sold by
Nobody in the catalogue publishes a price for this yet.
About
DeepSeek-V2-Lite — a text model from deepseek-ai.
It takes text and returns text. It was published in May 2024. The catalogue files it under chat. Its weights are published under the other licence, which attaches conditions the plain open licences do not.
Every current figure
- Maker
- deepseek-ai
- Register
- model
- Takes
- text
- Returns
- text
- Published
- May 2024
- Parameters
- 16 billion · read from its own weights
- Licence
- other
Known as 1 name
deepseek-ai/DeepSeek-V2-Lite