Userb1az/gemma-3-27b-it-abliterated-GGUF
Full fine-tune (fewer layers) vs google/gemma-3-27b-pt. Userb1az/gemma-3-27b-it-abliterated-GGUF matches part of google/gemma-3-27b-pt (808 of its 1247 tensors; the rest of google/gemma-3-27b-pt has no counterpart). On the shared part: Userb1az/gemma-3-27b-it-abliterated-GGUF is a GGUF (F16) of different weights. Fine-tune: 100% of the weights changed, across 62 of 62 layers.
Tensors changed: Embeddings 1/1, Norms 373/373, MLP 186/186, Attention 248/248