本文へスキップ
AI図鑑

DeepSeek-R1

強化学習で推論の連鎖を訓練し、MIT ライセンスで重みを公開した推論モデル

DeepSeek モデル オープンウェイト
入力テキストテキスト

本ページの本文は英語で提供されています。タイトルと導入は日本語化されています。

これは何か

DeepSeek-R1 is a reasoning model DeepSeek released in January 2025 that produces a long chain of thought before answering. It trains the model with reinforcement learning to generate reasoning steps on its own, rather than relying on large sets of human-labelled rationales. R1 shares the architecture scale of the V3 family, releases its weights under the MIT licence and publishes a technical report on its training method. After release, many distilled versions of R1 appeared, transferring its reasoning ability into smaller models.

なぜ覚えておく価値があるか

It fully open-sourced the weights of a frontier reasoning model under the MIT licence and published a reproducible RL training recipe; the wave of distilled versions that followed changed the cost structure of building one’s own reasoning capability.

主な仕様

Parameters
671B (MoE, 37B active)
Context window
128K tokens
Open weights
Yes (MIT licence)
Type
Reasoning model

対応する能力

関連する概念

同種の製品