ABBNDZ/gemma-4-E2B-it-AB-GGUF-Editor

Full fine-tune (fewer layers) vs google/gemma-4-E2B-it. ABBNDZ/gemma-4-E2B-it-AB-GGUF-Editor matches part of google/gemma-4-E2B-it (565 of its 2011 tensors; the rest of google/gemma-4-E2B-it has no counterpart). On the shared part: ABBNDZ/gemma-4-E2B-it-AB-GGUF-Editor is a GGUF (Q6_K_M) of different weights. Fine-tune: 100% of the weights changed, across 35 of 35 layers.

Tensors changed: Embeddings 2/2, Norms 0/247, MLP 105/105, other 71/71, Attention 140/140

On the Hub · Downloads on Model Pulse