zan/Qwen3.6-35B-A3B-DFlash-ja
Full fine-tune vs z-lab/Qwen3.6-35B-A3B-DFlash. Fine-tune: 100% of the weights changed, across 6 of 6 layers.
Tensors changed: Norms 26/26, MLP 18/18, Attention 12/12
Full fine-tune vs z-lab/Qwen3.6-35B-A3B-DFlash. Fine-tune: 100% of the weights changed, across 6 of 6 layers.
Tensors changed: Norms 26/26, MLP 18/18, Attention 12/12