mrcuddle/NemoMix-Magcap-12B
Full fine-tune vs MarinaraSpaghetti/NemoMix-Unleashed-12B. Fine-tune: 98% of the weights changed, across 40 of 40 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 81/81, MLP 117/120, Attention 156/160
3 derivatives checked
- mradermacher/NemoMix-Magcap-12B-i1-GGUF: Quantization
- mradermacher/NemoMix-Magcap-12B-GGUF: Quantization
- mrcuddle/Magcap-Adonis-12B: Full fine-tune