DeepSeek
Open-weight model family notable for efficient training at frontier scale.
Visão geral
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.
Grafo de tecnologias
Como DeepSeek se liga ao resto do stack.
Usa e depende de
- Transformer architecture Algorithms DeepSeek based on Transformer High ✓ source
Aplicado a
- MoE architecture Algorithms MoE used for DeepSeek High ✓ source
Ferramentas
Software que implementa ou se integra com DeepSeek.
Infrastructure
Alternativas
Comparações
Comparações detalhadas com as alternativas acima.