Retreatcost/Forgotten-directive-Neon-stock
Full fine-tune vs ReadyArt/Forgotten-Safeword-12B-v4.0. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 81/81, MLP 120/120, Attention 160/160, lm_head 1/1
3 derivatives checked
- mradermacher/Forgotten-directive-Neon-stock-i1-GGUF: Quantization
- mradermacher/Forgotten-directive-Neon-stock-GGUF: Quantization
- Retreatcost/KansenSakura-Erosion-RP-12b: Full fine-tune