Sorihon/CYDR-24B
Full fine-tune vs Delta-Vector/Rei-24B-KTO. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Norms 81/81, MLP 120/120, Attention 160/160
3 derivatives checked
- mradermacher/CYDR-24B-i1-GGUF: Quantization
- mradermacher/CYDR-24B-GGUF: Quantization
- Sorihon/Celestial-Order-24B-2.75: Full fine-tune