Steelskull/MSM-MS-Cydrion-22B
LoRA-style vs ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1. 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 56 of 56 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 168/168, Attention 224/224, lm_head 0/1
4 derivatives checked
- bartowski/MSM-MS-Cydrion-22B-GGUF: Same weights, converted
- BasedAGI/MSM-MS-Cydrion-22B-i1-GGUF: Quantization
- mradermacher/MSM-MS-Cydrion-22B-i1-GGUF: Quantization
- DoppelReflEx/Mimicore-GreenSnake-22B: Full fine-tune