mradermacher/Tiny-DarkLlama-SPIN-Implementation-i1-GGUF
Full fine-tune vs mrcuddle/Tiny-DarkLlama-SPIN-Implementation. mradermacher/Tiny-DarkLlama-SPIN-Implementation-i1-GGUF is a GGUF (Q6_K) of different weights. Fine-tune: 100% of the weights changed, across 22 of 22 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 45/45, MLP 66/66, Attention 88/88