nbeerbower/Huihui-Qwen3.5-0.8B-abliterated-Athanorlite-ORPO
LoRA-style vs huihui-ai/Huihui-Qwen3.5-0.8B-abliterated. 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, v_proj changed, in 24 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: Attention 24/216, Norms 0/129, Embeddings 0/4, MLP 72/124
2 derivatives checked
- mradermacher/Huihui-Qwen3.5-0.8B-abliterated-Athanorlite-ORPO-i1-GGUF: Quantization
- mradermacher/Huihui-Qwen3.5-0.8B-abliterated-Athanorlite-ORPO-GGUF: Same weights, converted