dannyliv/agent-guard-modernbert-base
LoRA-style vs answerdotai/ModernBERT-base. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of Wo, Wqkv changed, in 22 of 22 layers; norms, biases and embeddings are untouched.
Tensors changed: other 0/1, Norms 0/45, Embeddings 0/2, Attention 44/44, MLP 22/44