Edens-Gate/GnX
Full fine-tune vs Delta-Vector/Holland-4B-V1. Fine-tune: 91% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 0/1, MLP 96/96, Attention 128/128, Norms 26/65
1 derivatives checked
- mradermacher/GnX-GGUF: Same weights, converted