Mungert/Magistral-Small-2506-abliterated-GGUF
LoRA-style vs mistralai/Magistral-Small-2506. Mungert/Magistral-Small-2506-abliterated-GGUF is a GGUF (Q8_0) of different weights. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj changed, in 40 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 120/120, Attention 120/160, lm_head 0/1