TheDrummer/Magidonia-24B-v4.3
Full fine-tune (fewer layers) vs mistralai/Magistral-Small-2509. TheDrummer/Magidonia-24B-v4.3 matches part of mistralai/Magistral-Small-2509 (363 of its 585 tensors; the rest of mistralai/Magistral-Small-2509 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 8/81, MLP 120/120, Attention 160/160, lm_head 1/1
12 derivatives checked
- bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF: Same weights, converted
- mradermacher/Magidonia-24B-v4.3-i1-GGUF: Quantization
- mradermacher/Magidonia-24B-v4.3-GGUF: Quantization
- Mrd1011/TheDrummer_Magidonia-24B-v4.3-GGUF: Same weights, converted
- TigerKay/magidonia-24b-lumia-cot: LoRA-style
- Ateron/Predonia: Full fine-tune
- coder3101/Magidonia-24B-v4.3-heretic: Abliterated
- grayarea/Magidonia-24B-v4.3-heretic-v1.2: Abliterated
- WarlordHermes/Magidonia-24B-v4.3-creative-maybe-broken: LoRA-style
- MuXodious/Magidonia-24B-v4.3-absolute-heresy: Abliterated
- WarlordHermes/Magidonia-24B-v4.3-creative-ORPO: LoRA-style
- coder3101/Magidonia-24B-v4.3-heretic-v2: Abliterated