lhca521/Qwen3.6-35B-A3B-Abliterated-Heretic-GGUF
LoRA-style vs Qwen/Qwen3.6-35B-A3B. lhca521/Qwen3.6-35B-A3B-Abliterated-Heretic-GGUF is a GGUF (BF16/F32) of different weights. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate, o_proj changed, in 40 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/101, MLP 54/160, Attention 9/40, lm_head 0/1