king1oo1/deepfake-model
Partial fine-tune (fewer layers) vs google/siglip2-base-patch16-224. king1oo1/deepfake-model matches part of google/siglip2-base-patch16-224 (208 of its 408 tensors; the rest of google/siglip2-base-patch16-224 has no counterpart). On the shared part: Partial change: 0% of the weights changed (norms), in 0 of 12 layers.
Tensors changed: Embeddings 0/3, Norms 2/52, MLP 0/52, Attention 0/100, other 0/1