DeepSeek-MoE - a deepseek-ai Collection

deepseek-ai 's Collections

DeepSeek-Prover

DeepSeekCoder-V2

ESFT

DeepSeek-MoE

updated Aug 16

DeepSeek MoE series

deepseek-ai/deepseek-moe-16b-base

Text Generation • Updated Jan 12 • 17.9k • 83
deepseek-ai/deepseek-moe-16b-chat

Text Generation • Updated Feb 5 • 2.45k • 112
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

Paper • 2401.06066 • Published Jan 11 • 43