grimjim/magnum-consolidatum-v1-12b
Full fine-tune vs anthracite-org/magnum-v2.5-12b-kto. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 47/81, MLP 120/120, Attention 160/160, lm_head 1/1
5 derivatives checked
- mradermacher/magnum-consolidatum-v1-12b-i1-GGUF: Quantization
- mradermacher/magnum-consolidatum-v1-12b-GGUF: Quantization
- grimjim/Magnolia-v2-12B: Full fine-tune
- grimjim/Magnolia-v10-12B: Full fine-tune
- grimjim/Magnolia-v9-12B: Full fine-tune