clip_vit_large_14(pretrained: bool = False, overrides: object = {})Construct CLIP with a ViT-L/14 image tower.
Model Size
Parameters
pretrainedbool= FalseLoad the OpenAI WIT-400M checkpoint from the Lucid hub.
**overridesobject= {}Optional
CLIPConfig field overrides.Returns
CLIPModelBoth towers and the learned temperature.
Notes
Reference: Radford et al., ICML 2021 (arXiv:2103.00020), §2.4.
The best-performing variant in the paper, and the one whose text tower is widened along with the image tower — 768 wide with 12 heads against the base models' 512 and 8, at the same 12 layers.
Examples
>>> from lucid.models import clip_vit_large_14
>>> model = clip_vit_large_14()
>>> model.config.vision_layers, model.config.text_width
(24, 768)