Minthy/RouWei-0.6
Full fine-tune vs OnomaAIResearch/Illustrious-xl-early-release-v0. Fine-tune: 97% of the weights changed, across 11 of 12 layers.
Tensors changed: Embeddings 571/589, other 534/662, Attention 700/716, Norms 442/546
1 derivatives checked
- Minthy/RouWei-0.7: Full fine-tune