TheDrummer/Cydonia-24B-v3
Full fine-tune (fewer layers) vs mistralai/Mistral-Small-3.1-24B-Instruct-2503. TheDrummer/Cydonia-24B-v3 matches part of mistralai/Mistral-Small-3.1-24B-Instruct-2503 (363 of its 585 tensors; the rest of mistralai/Mistral-Small-3.1-24B-Instruct-2503 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 3/81, MLP 120/120, Attention 160/160, lm_head 1/1
6 derivatives checked
- bartowski/TheDrummer_Cydonia-24B-v3-GGUF: Same weights, converted
- mradermacher/Cydonia-24B-v3-i1-GGUF: Quantization
- mradermacher/Cydonia-24B-v3-GGUF: Quantization
- mlx-community/Cydonia-24B-v3-4bit: Quantization
- Vortex5/Chaos-Cydonia-24B: Full fine-tune
- Vortex5/WittyAthena-24b: Full fine-tune