Kaoeiri/MS-Hempantheonsel-Mull-v5x1.8RP-Cydonia-vXXX-24B-12
Full fine-tune (fewer layers) vs mistralai/Mistral-Small-3.1-24B-Instruct-2503. Kaoeiri/MS-Hempantheonsel-Mull-v5x1.8RP-Cydonia-vXXX-24B-12 matches part of mistralai/Mistral-Small-3.1-24B-Instruct-2503 (361 of its 585 tensors; the rest of mistralai/Mistral-Small-3.1-24B-Instruct-2503 has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Norms 81/81, MLP 120/120, Attention 160/160