JeremyLiShuhao/UD_model_v1
Full fine-tune vs Qwen/Qwen3Guard-Gen-4B. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 124/145, MLP 108/108, Attention 144/144
Full fine-tune vs Qwen/Qwen3Guard-Gen-4B. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 124/145, MLP 108/108, Attention 144/144