mradermacher/gemma-3-27b-it-heretic-GGUF
Full fine-tune (fewer layers) vs coder3101/gemma-3-27b-it-heretic. mradermacher/gemma-3-27b-it-heretic-GGUF matches part of coder3101/gemma-3-27b-it-heretic (808 of its 1247 tensors; the rest of coder3101/gemma-3-27b-it-heretic has no counterpart). On the shared part: mradermacher/gemma-3-27b-it-heretic-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 62 of 62 layers.
Tensors changed: Embeddings 1/1, Norms 0/373, MLP 186/186, Attention 248/248