RicardoEstep/RPBizkit-v4-12B_Lorablated
Partial fine-tune vs RicardoEstep/RPBizkit-v4-12B. Partial change: 34% of the weights changed (attention, mlp, norms), in 40 of 40 layers.
Tensors changed: Norms 81/81, MLP 39/120, Attention 39/160
3 derivatives checked
- mradermacher/RPBizkit-v4-12B_Lorablated-i1-GGUF: Quantization
- mradermacher/RPBizkit-v4-12B_Lorablated-GGUF: Quantization
- RicardoEstep/RPBizkit-v4-12B_Lorablated-GGUF: Same weights, converted