ZJU-Safety/DARWIN-Guard

Partial fine-tune vs Qwen/Qwen3Guard-Gen-8B. Partial change: 85% of the weights changed (attention, mlp, norms), in 36 of 36 layers.

Tensors changed: Embeddings 0/1, Norms 82/145, MLP 108/108, Attention 144/144, lm_head 0/1

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse