2024-05-06 · DeepSeek
A general mixture-of-experts model that activated only some experts per token to limit inference cost. The base and chat variants served different purposes.
The model name is used instead of a verified API ID.
2024-05-06 · DeepSeek
A general mixture-of-experts model that activated only some experts per token to limit inference cost. The base and chat variants served different purposes.
The model name is used instead of a verified API ID.