mp-juuuns/qwen3.5-4l-vocab40k-en-ko-headless
Full fine-tune vs Qwen/Qwen3.5-0.8B. Fine-tune: 100% of the weights changed, across 4 of 4 layers.
Tensors changed: Attention 18/20, Norms 11/13, MLP 12/12
Full fine-tune vs Qwen/Qwen3.5-0.8B. Fine-tune: 100% of the weights changed, across 4 of 4 layers.
Tensors changed: Attention 18/20, Norms 11/13, MLP 12/12