julianmb/Nex-N2.5-mini-ROCmFP4-GGUF
Full fine-tune vs nex-agi/Nex-N2.5-mini. julianmb/Nex-N2.5-mini-ROCmFP4-GGUF is a GGUF (T101/T100) of different weights. Fine-tune: 96% of the weights changed, across 0 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 0/101, MLP 0/40