zerofata/MS3.2-PaintedFantasy-Visage-v2-33B
Full fine-tune (fewer layers) vs zerofata/MS3.2-PaintedFantasy-v2-24B. zerofata/MS3.2-PaintedFantasy-v2-24B matches part of zerofata/MS3.2-PaintedFantasy-Visage-v2-33B (363 of its 525 tensors; the rest of zerofata/MS3.2-PaintedFantasy-Visage-v2-33B has no counterpart). On the shared part: Fine-tune: 94% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 0/1, Norms 22/81, MLP 120/120, Attention 160/160, lm_head 0/1
4 derivatives checked
- bartowski/zerofata_MS3.2-PaintedFantasy-Visage-v2-33B-GGUF: Same weights, converted
- mradermacher/MS3.2-PaintedFantasy-Visage-v2-33B-i1-GGUF: Quantization
- mradermacher/MS3.2-PaintedFantasy-Visage-v2-33B-GGUF: Quantization
- DevQuasar/zerofata.MS3.2-PaintedFantasy-Visage-v2-33B-GGUF: Same weights, converted