Abdulhanan2006/LogicLumina-L3-13B-v2
Full fine-tune vs Abdulhanan2006/LogicLumina-L3-13B. Fine-tune: 95% of the weights changed, across 39 of 40 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 29/81, MLP 114/120, Attention 152/160
2 derivatives checked
- mradermacher/LogicLumina-L3-13B-v2-i1-GGUF: Quantization
- mradermacher/LogicLumina-L3-13B-v2-GGUF: Quantization