Model card: optimizer routing

README.md

@@ -104,11 +104,11 @@ sharpens the output distribution and stabilises generations.
 | Resolution | About 1 megapixel, aspect-ratio buckets |
 | Text | Prompts up to 2,304 tokens; 10% of captions dropped to the empty prompt |
 | Objective | The base's flow-matching objective; noise levels from a truncated logit-normal (μ 1.09, σ 0.95, truncated at 0.95), plus 1% uniform and 1% pure noise |
-| Optimizer | [dionw](https://github.com/JTriggerFish/dionw): Dion (row-selected NorMuon) on weight matrices, AdamW on the rest |
+| Optimizer | [dionw](https://github.com/JTriggerFish/dionw): Dion (row-selected NorMuon) on the attention and MLP weight matrices (image blocks and the text embedder's blocks); AdamW on the input embeddings (latent, text and timestep), the AdaLN modulation projections, the output head, norms and biases |
 | Learning rate | 9e-6, AdamW-equivalent for every parameter |
 | Schedule | 200-step linear warmup, constant to step 10,500, then a 2,000-step 1 − √ cooldown to 0 |
 | Dion matrices | 25% of each block's rows updated per step (blocks with both sides ≥ 1024), Gram Newton–Schulz, heavy-ball momentum 0.95, NorMuon row normalization β₂ 0.975 |
-| AdamW parameters | β = (0.9, 0.975), ε 1e-8; includes the fused conditioning (AdaLN) projections |
+| AdamW parameters | β = (0.9, 0.975), ε 1e-8 |
 | Weight decay | 0.01 on Dion matrices, none on AdamW parameters |
 | Gradient clipping | Global norm 1.0 |
 | Released weights | EMA of the weights (decay 0.999, fp32, updated every step) at step 12,500, stored in bfloat16 (`rope.bands` in float32, as in the base release) |