jeiku/AuraFinal12B
Full fine-tune vs MarinaraSpaghetti/NemoReRemix-12B. Fine-tune: 98% of the weights changed, across 40 of 40 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 39/81, MLP 117/120, Attention 156/160
1 derivatives checked
- mradermacher/AuraFinal12B-GGUF: Quantization