EldritchLabs/KrakenSakura-Maelstrom-12B-v1

Full fine-tune vs ChaoticNeutrals/Captain_Eris_Noctis-12B-v0.420. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Norms 81/81, MLP 120/120, Attention 160/160

2 derivatives checked

• Naphula/KrakenSakura-Maelstrom-12B-v1-GGUF: Same weights, converted
• DarkArtsForge/Morbid-Miasma-12B: Full fine-tune

On the Hub · Downloads on Model Pulse