# Cross-modal Distillation

TinyCLIP is an innovative cross-modal distillation approach for large-scale language-image pre-trained models, achieving the optimal balance between speed and accuracy through affinity mimicking and weight inheritance techniques.

TinyCLIP is an innovative cross-modal distillation method for large-scale language-image pre-trained models, achieving efficient training of small-scale CLIP models through affinity mimicking and weight inheritance techniques.

This is a Japanese CLIP text/image encoder model converted from the English CLIP model through distillation techniques.