RicardoEstep/RPBizkitRemiX-v2-12B
Full fine-tune vs RicardoEstep/RPBizkit-v2-12B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Norms 81/81, MLP 120/120, Attention 160/160
3 derivatives checked
- mradermacher/RPBizkitRemiX-v2-12B-i1-GGUF: Quantization
- mradermacher/RPBizkitRemiX-v2-12B-GGUF: Quantization
- RicardoEstep/RPBizkitRemiX-v2-12B-GGUF: Same weights, converted