Darkknight535/Magidonia-24B-v4.3-heretic-v3
Full fine-tune (fewer layers) vs mistralai/Magistral-Small-2509. Darkknight535/Magidonia-24B-v4.3-heretic-v3 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
2 derivatives checked
- mradermacher/Magidonia-24B-v4.3-heretic-v3-GGUF: Quantization
- mradermacher/Magidonia-24B-v4.3-heretic-v3-i1-GGUF: Quantization