mfielding92/littlemonster-reasoning-12B-QKVO-heretic-GGUF
Full fine-tune (fewer layers) vs p-e-w/gemma-3-12b-it-heretic. mfielding92/littlemonster-reasoning-12B-QKVO-heretic-GGUF matches part of p-e-w/gemma-3-12b-it-heretic (626 of its 1065 tensors; the rest of p-e-w/gemma-3-12b-it-heretic has no counterpart). On the shared part: mfielding92/littlemonster-reasoning-12B-QKVO-heretic-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