Doctor-Shotgun/MS3.2-24B-Magnum-Diamond
Full fine-tune (fewer layers) vs mistralai/Mistral-Small-3.2-24B-Instruct-2506. Doctor-Shotgun/MS3.2-24B-Magnum-Diamond matches part of mistralai/Mistral-Small-3.2-24B-Instruct-2506 (363 of its 585 tensors; the rest of mistralai/Mistral-Small-3.2-24B-Instruct-2506 has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 0/81, MLP 120/120, Attention 160/160, lm_head 1/1
14 derivatives checked
- Doctor-Shotgun/MS3.2-24B-Magnum-Diamond-GGUF: Same weights, converted
- mradermacher/MS3.2-24B-Magnum-Diamond-i1-GGUF: Quantization
- mradermacher/MS3.2-24B-Magnum-Diamond-GGUF: Quantization
- DevQuasar/Doctor-Shotgun.MS3.2-24B-Magnum-Diamond-GGUF: Same weights, converted
- knifeayumu/Cydonia-v4-MS3.2-Magnum-Diamond-24B: Full fine-tune
- MuXodious/MS3.2-24B-Magnum-Diamond-PaperWitch-heresy: Abliterated
- knifeayumu/Cydonia-v4.1-MS3.2-Magnum-Diamond-24B: Full fine-tune
- Vortex5/MS3.2-24B-Astral-Mirage: Full fine-tune
- Vortex5/MS3.2-24B-Chaos-Skies: Full fine-tune
- Vortex5/MS3.2-24B-Omega-Diamond: Full fine-tune
- Guilherme34/Big-Firefly: Full fine-tune
- grimjim/Modicum-of-Doubt-v1-24B: Full fine-tune
- Azazelle/MS3.2-24b-Seraphim: Full fine-tune
- grimjim-merge-workshop/demi-MS3.2-24B-Magnum-Diamond: Full fine-tune