knifeayumu/Lite-Cydonia-22B-v1.1-75-25

Full fine-tune vs TheDrummer/Cydonia-22B-v1.1. Fine-tune: 99% of the weights changed, across 56 of 56 layers.

Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 63/113, MLP 168/168, Attention 224/224

2 derivatives checked

• mradermacher/Lite-Cydonia-22B-v1.1-75-25-GGUF: Quantization
• mradermacher/Lite-Cydonia-22B-v1.1-75-25-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse