TheDrummer/Cydonia-Redux-22B-v1.1
Full fine-tune vs mistralai/Mistral-Small-Instruct-2409. Fine-tune: 100% of the weights changed, across 56 of 56 layers.
Tensors changed: Embeddings 1/1, Norms 61/113, MLP 168/168, Attention 224/224, lm_head 1/1
4 derivatives checked
- bartowski/TheDrummer_Cydonia-Redux-22B-v1.1-GGUF: Same weights, converted
- mradermacher/Cydonia-Redux-22B-v1.1-i1-GGUF: Quantization
- mradermacher/Cydonia-Redux-22B-v1.1-GGUF: Quantization
- ReadyArt/Dark-Desires-22B-v1.5: LoRA-style