A continuaciónSiguiente guía
Imbuir agentes de razonamiento
Empresas
GUÍA de empresas
DeepSeek-V3 and DeepSeek-R1 are open-weight model releases with different technical contributions.
Escuche esta guíaNarrado por IA · ~2 min
V3 uses a mixture-of-experts architecture; R1 applies reinforcement learning and a multi-stage post-training pipeline to reasoning. Reported GPU-hour figures describe a specific V3 training run, not the full research cost or the cost to train R1.
The DeepSeek-V3 report describes a 671B-parameter mixture-of-experts model with 37B activated per token. It reports 2.788 million H800 GPU-hours for the full V3 training run; this compute estimate is not the total cost of the research program and does not state the cost of training R1. DeepSeek-R1 builds on DeepSeek-V3-Base. Its paper describes a multi-stage pipeline: cold-start supervised fine-tuning, reasoning-focused reinforcement learning, rejection sampling and supervised fine-tuning, then a second RL stage. The paper evaluates verifiable tasks such as mathematics, coding competitions, and STEM. It also describes smaller distilled models based on Qwen and Llama families.
Inspecting the V3 technical report’s active-versus-total parameter description for its MoE architecture
Comparing R1’s reasoning evaluation on mathematics, coding, and STEM tasks
Studying the stages used to build R1 from a V3 base model
Using smaller R1-distilled models based on Qwen and Llama checkpoints for research
DeepSeek’s reports contribute open-weight model artifacts and technical descriptions of MoE training and RL-based reasoning. Results should be tied to each model, checkpoint, benchmark, and training stage. Reported compute estimates are narrower than total research, infrastructure, and data costs.
Boletín gratuito
Tres noticias verificadas sobre IA cada mañana de lunes a viernes, explicadas con claridad. Gratis para siempre y sin anuncios.
Un correo cada día laborable. Date de baja con un clic. Nunca vendemos ni compartimos tu dirección.
Ponte a prueba
Corrección inmediata en cada respuesta y un certificado para compartir, con un ID verificable, cuando apruebas un curso.
Apoya la educación gratuita sobre IA. AI Understanding es una organización sin fines de lucro 501(c)(3): sin anuncios ni muros de pago, nunca. Hacer una donación
DeepSeek-V3 and DeepSeek-R1 are open-weight model releases with different technical contributions. V3 uses a mixture-of-experts architecture; R1 applies reinforcement learning and a multi-stage post-training pipeline to reasoning. Reported GPU-hour figures describe a specific V3 training run, not the full research cost or the cost to train R1.
The V3 report describes 671B total parameters and 37B active per token in its MoE architecture.
The R1 paper describes reinforcement-learning-based reasoning and the project released model weights; the paper does not imply every capability is achieved by RL alone.
The V3 report lists 2.788M H800 GPU-hours for the full training run; this is not a full research-cost figure or an estimate for R1 training.
The R1 report describes RL using verifiable reward signals for reasoning tasks, alongside other stages in the full R1 pipeline.
V3 introdujo técnicas como atención latente de múltiples cabezales y un esquema de equilibrio de carga auxiliar sin pérdidas para entrenar su MoE de manera eficiente.
sigue aprendiendo
Más guías seleccionadas para este tema.
A continuaciónSiguiente guía
Imbuir agentes de razonamiento
Empresas