DeepSeek-Coder-V2 236B

A coding MoE continued from an intermediate DeepSeek-V2 checkpoint, with 236B total and 21B active parameters and 128K context.

LegacyCodingLanguageOpen weights

MODEL NUMBER225

Specifications

Only published specifications are shown.

Total parameters

236B

Active parameters

21B

Architecture

MoE

Context

128K

Input modalities

Text

Output modalities

Text

Open weights

Yes

Status

Legacy

A coding MoE continued from an intermediate DeepSeek-V2 checkpoint, with 236B total and 21B active parameters and 128K context.

PreviousDeepSeek Coder— · 16K ctx

CurrentDeepSeek-Coder-V2 236B236B · 128K ctx

2024-06-14API launch

The deepseek-coder API upgraded to DeepSeek-Coder-V2-0614, ahead of the open-weight release.

2024-06-17Open weights

DeepSeek-Coder-V2 236B released model weights.

Select a card to view the related model.