mb4063/Qwythos-27B-v1-ROCmFP4
Full fine-tune vs empero-ai/Qwythos-27B-v1. mb4063/Qwythos-27B-v1-ROCmFP4 is a GGUF (T101/T100) of different weights. Fine-tune: 100% of the weights changed, across 0 of 64 layers.
Tensors changed: Embeddings 1/1, Norms 0/161