DeepSeek
Open-weight model family notable for efficient training at frontier scale.
Überblick
DeepSeek is an open-weight model family whose published training methods attracted attention for reaching competitive quality at lower reported cost. It solves the cost question in training rather than in inference, which is where most optimisation effort goes. It exists as evidence that architecture and training-schedule choices matter enough to change what a given budget can produce, and its weights and methods are published.
Technologiegraph
Wie DeepSeek mit dem übrigen Stack zusammenhängt.
Nutzt und hängt ab von
- Transformer architecture Algorithms DeepSeek based on Transformer High ✓ source
Angewendet auf
- MoE architecture Algorithms MoE used for DeepSeek High ✓ source
Werkzeuge
Software, die DeepSeek implementiert oder integriert.
Infrastructure
Alternativen
Vergleiche
Detaillierte Gegenüberstellungen mit den Alternativen oben.