Eliasfpv28/Kolibri-1-Q3_K_S-GGUF
Full fine-tune vs Aleph-Alpha/Kolibri-1-BF16. Eliasfpv28/Kolibri-1-Q3_K_S-GGUF is a GGUF (Q3_K_S) of different weights. Fine-tune: 98% of the weights changed, across 50 of 50 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 50/201, MLP 150/200, Attention 200/200