mlabonne/Qwen3-30B-A3B-abliterated
LoRA-style vs Qwen/Qwen3-30B-A3B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, o_proj, q_proj, v_proj changed, in 38 of 48 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/193, MLP 0/2613, Attention 152/192, lm_head 0/1
3 derivatives checked
- mradermacher/Qwen3-30B-A3B-abliterated-GGUF: Full fine-tune
- mradermacher/Qwen3-30B-A3B-abliterated-i1-GGUF: Full fine-tune
- DevQuasar/mlabonne.Qwen3-30B-A3B-abliterated-GGUF: LoRA-style