wangzhang/gemma-4-31B-it-abliterated-GGUF
LoRA-style (fewer layers) vs wangzhang/gemma-4-31B-it-abliterated. wangzhang/gemma-4-31B-it-abliterated-GGUF matches part of wangzhang/gemma-4-31B-it-abliterated (772 of its 1188 tensors; the rest of wangzhang/gemma-4-31B-it-abliterated has no counterpart). On the shared part: wangzhang/gemma-4-31B-it-abliterated-GGUF is a GGUF (F16) of different weights. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, k_proj, o_proj, q_proj, v_proj changed, in 42 of 60 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/361, MLP 30/180, Attention 111/230