mlx-community/olmOCR-7B-0225-preview-bf16
Full fine-tune vs Qwen/Qwen2-VL-7B-Instruct. Fine-tune: 99% of the weights changed, across 32 of 32 layers.
Tensors changed: Attention 128/128, MLP 131/132, Norms 87/130, lm_head 1/1
Full fine-tune vs Qwen/Qwen2-VL-7B-Instruct. Fine-tune: 99% of the weights changed, across 32 of 32 layers.
Tensors changed: Attention 128/128, MLP 131/132, Norms 87/130, lm_head 1/1