Moe
Exploring DeepSeek Version 3: A Technical Overview
The launch of DeepSeek Version 3 has sparked considerable excitement within the AI community, thanks to its remarkable capabilities and cost-efficiency. As an advanced open-weight large language
Read More
Unlocking Mixture-of-Experts (MoE) LLM : Your MoE model can be embedding model for free
Mixture-of-experts (MoE) LLM can be used as an embedding model for free. I recently found an interesting paper titled “Your Mixture-of-Experts LLM is Secretly an Embedding Model for Free.”
Read More