Model Architecture & Training MethodsPearce & Song

Reconciling Kaplan and Chinchilla Scaling Laws

Made by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made

Reconciling Kaplan and Chinchilla Scaling Laws

Why it matters

Showed that the conflict between the two laws stems from counting non-embedding parameters and from analysis at small scale

Source — Primary sources first; secondary reports are labelled “Press”

Paperarxiv.orghttps://arxiv.org/abs/2406.12907

Added in Week 35, 2026 · See that week

On the map — ⑪ Model Architecture line

  1. Previous stopDeepSeek-V2
  2. This recordReconciling Kaplan and Chinchilla Scaling Laws
  3. Next stopByte Latent Transformer
See it on the map

Same week

SB Intuitions releases Sarashina1 series 7B/13B/65B Japanese LLMsOfficialMaxime Labonne publishes AbliterationOfficialOpenVLAPaperMagpiePaper

Nearby on the same axis

DeepSeek-V2PaperSakana AI announces Evolutionary Model Merge, releases EvoLLM-JP and EvoVLM-JPOfficialBeyond Chinchilla-OptimalPaperKeller Jordan releases the Muon optimizerOfficial