Retreatcost/KansenSakura-Radiance-RP-12b
Full fine-tune vs Epiculous/Azure_Dusk-v0.2. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 66/81, MLP 120/120, Attention 160/160, lm_head 1/1
4 derivatives checked
- mradermacher/KansenSakura-Radiance-RP-12b-GGUF: Quantization
- mradermacher/KansenSakura-Radiance-RP-12b-i1-GGUF: Quantization
- Vortex5/Radiant-Shadow-12B: Partial fine-tune
- Vortex5/Luminous-Shadow-12B: Full fine-tune