zer0int/CLIP-ViT-L-14-Cross-Attn-Read-NoRead-ModeMUX

Full fine-tune vs openai/clip-vit-large-patch14. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: other 3/3, Embeddings 4/4, Norms 150/150, MLP 144/144, Attention 288/288

On the Hub · Downloads on Model Pulse