charlieduzstuf/Qwable-Ex
Full fine-tune vs DarkKitsune/Qwen3.5-9B-Qworus-V2. Fine-tune: 94% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 87/215, Attention 203/332, MLP 96/208, Embeddings 0/3
Full fine-tune vs DarkKitsune/Qwen3.5-9B-Qworus-V2. Fine-tune: 94% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 87/215, Attention 203/332, MLP 96/208, Embeddings 0/3