Ir para o conteúdo
Atlas de IA

DeepSeek-R1

Um modelo de raciocínio treinado com RL sobre cadeias de pensamento, com pesos abertos sob licença MIT

DeepSeek Modelo Pesos abertos
entradaTextoTexto

O texto completo é apresentado em inglês; o título e o resumo estão traduzidos.

O QUE É

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.

Por que vale a pena lembrar

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.

Especificações-chave

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

Capacidades

Conceitos relacionados

Produtos semelhantes