Mai departeUrmătorul ghid
Îmbunătăți agenții de raționament
Companii
GHID Firme
DeepSeek-V3 and DeepSeek-R1 are open-weight model releases with different technical contributions.
Ascultă acest ghidNarativ AI · ~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.
Buletin gratuit
Trei povești AI verificate în fiecare dimineață de zi lucrătoare, scrise în engleză simplă. Gratuit pentru totdeauna, fără reclame.
Un e-mail în fiecare zi lucrătoare. Dezabonare cu un singur clic. Nu vindem niciodată și nu împărtășim adresa ta.
Testează-te
Feedback instantaneu la fiecare răspuns și un certificat partajabil cu un ID verificabil după ce parcurgi un curs.
Susține educația AI gratuită. AI Understanding este o organizație nonprofit 501(c)(3) — fără reclame, fără barieră de plată, pentru totdeauna. Fă o donație
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 a introdus tehnici precum atenția latentă cu mai multe capete și o schemă de echilibrare a sarcinii fără pierderi auxiliare pentru a-și antrena eficient MoE.
Continuați să învățați
Mai multe ghiduri alese pentru acest subiect
Mai departeUrmătorul ghid
Îmbunătăți agenții de raționament
Companii