Saltar al contenido
Atlas de IA

DeepSeek-R1

Un modelo de razonamiento entrenado con RL sobre cadenas de pensamiento, con pesos abiertos bajo licencia MIT

DeepSeek Modelo Pesos abiertos
entradaTextoTexto

El texto completo se presenta en inglés; el título y el resumen están traducidos.

QUÉ ES

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 qué merece la pena recordarlo

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.

Especificaciones clave

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

Capacidades

Conceptos relacionados

Productos similares