AuriAetherwiing/MN-12B-Starcannon-v3
Full fine-tune vs anthracite-org/magnum-v2-12b. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 3/81, MLP 120/120, Attention 160/160, lm_head 1/1
5 derivatives checked
- mradermacher/MN-12B-Starcannon-v3-i1-GGUF: Quantization
- bartowski/MN-12B-Starcannon-v3-GGUF: Quantization
- mradermacher/MN-12B-Starcannon-v3-GGUF: Quantization
- GalrionSoftworks/MN-LooseCannon-12B-v1: Full fine-tune
- pot99rta/UltraPatriMerge-12B: Full fine-tune
3 other repos hold byte-for-byte identical weight files.