arisridwan/islamgpt-id-gguf
Full fine-tune (fewer layers) vs google/gemma-4-E2B. arisridwan/islamgpt-id-gguf matches part of google/gemma-4-E2B (565 of its 2011 tensors; the rest of google/gemma-4-E2B has no counterpart). On the shared part: arisridwan/islamgpt-id-gguf is a GGUF (F16) of different weights. Fine-tune: 100% of the weights changed, across 35 of 35 layers.
Tensors changed: Embeddings 2/2, Norms 220/247, MLP 105/105, other 71/71, Attention 140/140