knifeayumu/Cydonia-v1.2-Magnum-v4-22B

Full fine-tune vs TheDrummer/Cydonia-22B-v1.2. Fine-tune: 100% of the weights changed, across 56 of 56 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 60/113, MLP 168/168, Attention 224/224

2 derivatives checked

• mradermacher/Cydonia-v1.2-Magnum-v4-22B-i1-GGUF: Quantization
• knifeayumu/Cydonia-v1.2-Magnum-v4-22B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse