elyssiaelysium/elyssia
LoRA-style vs huihui-ai/Huihui-Qwen3.5-4B-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 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/4, Norms 0/203, Attention 32/320, MLP 96/196
1 derivatives checked
- mradermacher/elyssia-GGUF: Same weights, converted