Disya/amoral-cogito-Zara-14B-ties
Full fine-tune vs aixonlab/Zara-14b-v1.2. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 45/97, MLP 144/144, Attention 315/336, lm_head 1/1
2 derivatives checked
- mradermacher/amoral-cogito-Zara-14B-ties-GGUF: Quantization
- mradermacher/amoral-cogito-Zara-14B-ties-i1-GGUF: Quantization