over-show/gemma-4-e2b-it-text-only-4bit
Full fine-tune vs mlx-community/gemma-4-e2b-it-4bit. Fine-tune: 93% of the weights changed, across 35 of 35 layers.
Tensors changed: Embeddings 3/6, other 140/245, MLP 141/315, Norms 0/132, Attention 154/300
Full fine-tune vs mlx-community/gemma-4-e2b-it-4bit. Fine-tune: 93% of the weights changed, across 35 of 35 layers.
Tensors changed: Embeddings 3/6, other 140/245, MLP 141/315, Norms 0/132, Attention 154/300