knifeayumu/Lite-Cydonia-22B-v1.1-50-50-GGUF

Same weights, converted vs knifeayumu/Lite-Cydonia-22B-v1.1-50-50. Same weights stored in another dtype (F16 → F16/F32).

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

On the Hub · Downloads on Model Pulse