Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

DeepSeekMoE 145B Base

Model basics

Reasoning traces

Not supported

Context length

4K tokens

Max output length

No data

Model type

基础大模型

Release date

2024-01-11

Model file size

288GB

MoE architecture

Total params / Active params

1446.0B / N/A

Knowledge cutoff

No data

Inference modes

No mode data

DeepSeekMoE 145B Base

Open source & experience

Code license

MIT License

Weights license

DEEPSEEK LICENSE AGREEMENT- 免费商用授权

GitHub repo

https://github.com/deepseek-ai/DeepSeek-MoE

Hugging Face

Hugging Face link unavailable

Live demo

No live demo

DeepSeekMoE 145B Base

Official resources

Paper

DeepSeek LLM: Scaling Open-Source Language Models with Longtermism

DataLearnerAI blog

No blog post yet

DeepSeekMoE 145B Base

API details

API speed

No data

No public API pricing yet.

DeepSeekMoE 145B Base

Benchmark Results

No benchmark data to show.

DeepSeekMoE 145B Base

Publisher

DeepSeek-AI

View publisher details

DeepSeekMoE 145B Base

Model Overview

DeepSeekMoE是幻方量化旗下大模型企业DeepSeek开源的一个混合专家大模型，也是目前已知的中国第一个开源的MoE大模型。

DeepSeekMoE 145B Base是其1446亿参数的版本。

DataLearner 官方微信

欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送