TheDrummer/Cydonia-ReduX-22B-v1

Full fine-tune vs mistralai/Mistral-Small-Instruct-2409. Fine-tune: 99% of the weights changed, across 56 of 56 layers.

Tensors changed: Embeddings 0/1, Norms 28/113, MLP 168/168, Attention 224/224, lm_head 1/1

3 derivatives checked

• bartowski/TheDrummer_Cydonia-ReduX-22B-v1-GGUF: Same weights, converted
• mradermacher/Cydonia-ReduX-22B-v1-i1-GGUF: Quantization
• mradermacher/Cydonia-ReduX-22B-v1-GGUF: Quantization

On the Hub · Downloads on Model Pulse