wangzhang/Qwen3.8-27B-abliterated
LoRA-style vs Qwen/Qwen3.8-27B. 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 64 of 64 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/209, Attention 64/448, MLP 64/192, Embeddings 0/1, lm_head 0/1
3 derivatives checked
- mradermacher/Qwen3.8-27B-abliterated-GGUF: Full fine-tune
- mradermacher/Qwen3.8-27B-abliterated-i1-GGUF: Full fine-tune
- marafx2007/Qwen3.8-27B-abliterated-GGUF: Full fine-tune
1 other repos hold byte-for-byte identical weight files.