zhixiangwei/hqclip-openai-large-ft-vlm1b
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 5/5, Norms 150/150, MLP 144/144, Attention 288/288
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 5/5, Norms 150/150, MLP 144/144, Attention 288/288