MayZhou/e5-small-lora-ai-generated-detector
LoRA-style vs intfloat/e5-small. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of key, query, value changed, in 12 of 12 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/5, Norms 0/48, Attention 36/96, other 0/50