Ateron/Sketch-Cydonia
Full fine-tune vs TheDrummer/Cydonia-24B-v4.3. Fine-tune: 92% of the weights changed, across 39 of 40 layers.
Tensors changed: Embeddings 0/1, Norms 24/81, MLP 117/120, Attention 156/160, lm_head 0/1
5 derivatives checked
- mradermacher/Sketch-Cydonia-i1-GGUF: Quantization
- mradermacher/Sketch-Cydonia-GGUF: Quantization
- McG-221/Sketch-Cydonia-mlx-8Bit: Quantization
- Ateron/Sketch-Cydonia_V1.1: Full fine-tune
- MrRikyz/FusionPulse-24B: Full fine-tune