gokaygokay/Florence-2-Flux
Full fine-tune vs microsoft/Florence-2-base. Fine-tune: 100% of the weights changed, across 6 of 6 layers.
Tensors changed: Embeddings 8/9, Norms 166/166, other 106/107, Attention 240/240, MLP 144/144
Full fine-tune vs microsoft/Florence-2-base. Fine-tune: 100% of the weights changed, across 6 of 6 layers.
Tensors changed: Embeddings 8/9, Norms 166/166, other 106/107, Attention 240/240, MLP 144/144