DeepSeek-V2:高性能混合专家语言模型,训练经济且推理高效

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Branch1Tags0

Introduction

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Customize your domain
425.02 K544Visit GitHub