RicardoEstep/RPBizkit-v4-12B

Full fine-tune vs ChaoticNeutrals/Nera_Noctis-12B. 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

• RicardoEstep/RPBizkit-v4-12B-GGUF: Same weights, converted
• RicardoEstep/RPBizkit-v4-12B_Lorablated: Partial fine-tune

On the Hub · Downloads on Model Pulse