Nimbz/Prosopon-31B
Full fine-tune vs AuriAetherwiing/G4-31B-Musica-v1. Fine-tune: 94% of the weights changed, across 60 of 60 layers.
Tensors changed: Embeddings 0/4, Norms 180/523, other 0/62, MLP 180/261, Attention 230/338
3 derivatives checked
- Nimbz/Prosopon-31B-GGUF: Quantization (fewer layers)
- mradermacher/Prosopon-31B-i1-GGUF: Quantization (fewer layers)
- mradermacher/Prosopon-31B-GGUF: Quantization (fewer layers)