nbeerbower/Huihui-Qwen3.5-9B-abliterated-Grimoire-DPO
LoRA-style (fewer layers) vs huihui-ai/Huihui-Qwen3.5-9B-abliterated. nbeerbower/Huihui-Qwen3.5-9B-abliterated-Grimoire-DPO matches part of huihui-ai/Huihui-Qwen3.5-9B-abliterated (427 of its 775 tensors; the rest of huihui-ai/Huihui-Qwen3.5-9B-abliterated has no counterpart). On the shared part: 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 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, MLP 96/96, Attention 32/224, Norms 0/105
3 derivatives checked
- mradermacher/Huihui-Qwen3.5-9B-abliterated-Grimoire-DPO-i1-GGUF: Quantization
- fairy322/Huihui-Qwen3.5-9B-abliterated-Grimoire-DPO-GGUF: Same weights, converted
- mradermacher/Huihui-Qwen3.5-9B-abliterated-Grimoire-DPO-GGUF: Same weights, converted