DeepSeek-V2
Free while signed in. Answers cite the passages they came from.
First page
The curator’s take
a strong MoE model comprising 236B parameters, of which 21B are activated for each token; supports a context length of 128K tokens and uses Multi-head Latent Attention (MLA) for efficient inference by compressing the Key-Value (KV) cache into a latent vector; DeepSeek-V2 and its chat versions achieve top-tier performance among open-source models.
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack