deepseek-ai/DeepSeek-V2
DeepSeek-V2 is a Mixture-of-Experts large language model with sparse activation, developed by DeepSeek AI.
★5k stars Language Models
Not currently ranked — collecting fresh signals.
star history
The repository contains weights, training code, and configuration for DeepSeek-V2, a 236B parameter MoE model. It employs Multi-head Latent Attention (MLA) and DeepSeekMoE architecture with 16 experts per token for efficient sparse computation. The model is designed to be economical and efficient compared to dense models of equivalent capacity.
Frequently asked
- What is deepseek-ai/DeepSeek-V2?
- DeepSeek-V2 is a Mixture-of-Experts large language model with sparse activation, developed by DeepSeek AI.
- Is DeepSeek-V2 open source?
- Yes — deepseek-ai/DeepSeek-V2 is open source, released under the MIT license.
- How popular is DeepSeek-V2?
- deepseek-ai/DeepSeek-V2 has 5k stars on GitHub.
- Where can I find DeepSeek-V2?
- deepseek-ai/DeepSeek-V2 is on GitHub at https://github.com/deepseek-ai/DeepSeek-V2.