huihui-ai/Huihui4-48B-A4B-abliterated
LoRA-style vs TeichAI/gemma-4-26B-A4B-it-Claude-Opus-Distill. 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 30 of 30 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/4, Norms 0/433, other 0/62, MLP 90/171, Attention 115/223
3 derivatives checked
- mradermacher/Huihui4-48B-A4B-abliterated-i1-GGUF: Quantization
- mradermacher/Huihui4-48B-A4B-abliterated-GGUF: Quantization
- cesarsal1nas/Huihui4-48B-A4B-abliterated-GGUF: Quantization