QuantFactory/Veritas-12B-GGUF
Full fine-tune (fewer layers) vs soob3123/amoral-gemma3-12B-v2-qat. QuantFactory/Veritas-12B-GGUF matches part of soob3123/amoral-gemma3-12B-v2-qat (626 of its 1065 tensors; the rest of soob3123/amoral-gemma3-12B-v2-qat has no counterpart). On the shared part: QuantFactory/Veritas-12B-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 0/289, MLP 144/144, Attention 192/192