ConceptChinchilla Scaling Law / 缩放定律
Chinchilla Scaling Laws
A set of large language model training principles proposed by DeepMind, describing the optimal ratio between model parameter count and training data volume. The laws indicate that, under a fixed compute budget, model size and training data should be scaled proportionally to achieve optimal performance.
Timeline (last 90 days)
Aug 28
The core finding of the Chinchilla scaling law is that under a fixed compute budget, simultaneously increasing model parameters and training data volume is required to achieve optimal performance.
Unverified60%