Vortex5/MS3.2-24B-Fiery-Lynx
LoRA-style vs ConicCat/Mistral-Small-3.2-AntiRep-24B. 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 40 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/81, MLP 120/120, Attention 160/160
2 derivatives checked
- mradermacher/MS3.2-24B-Fiery-Lynx-i1-GGUF: Quantization
- mradermacher/MS3.2-24B-Fiery-Lynx-GGUF: Quantization