mradermacher/Decka-4B-i1-GGUF
Full fine-tune vs mrzenin/Decka-4B. mradermacher/Decka-4B-i1-GGUF is a GGUF (Q6_K) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 0/81, MLP 96/96, Attention 32/32