Instructions to use HopitAI/moda-pro-lite with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- OpenCLIP
How to use HopitAI/moda-pro-lite with OpenCLIP:
import open_clip model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:HopitAI/moda-pro-lite') tokenizer = open_clip.get_tokenizer('hf-hub:HopitAI/moda-pro-lite') - Notebooks
- Google Colab
- Kaggle
Commit History
-
Move serving recipe to moda-pro-lite-plus
Verified signature16a5669 -
Card: MODA Pro Lite (bare encoder); recipe moved to moda-pro-lite-plus
Verified signaturee3797c9 -
Card: MODA Pro Lite+ — results, recipe, serving_ann.py; process detail removed
Verified signaturefbc2be0
-
card: add booking link for pilots and catalog evaluation
Verified signaturec63f26f -
correction: Atlas gain is not statistically significant; label KAGL/Polyvore as significant
Verified signaturee0ec375 -
card: terminology cleanup
Verified signatureb673e9d -
card: training described at outcome level only
Verified signature24a8d0d -
card: MODA Pro described by result only
Verified signature52d7711 -
config: tokenizer resolves from this repo (trimmed vocab)
Verified signature37c69cc -
card: 213M in family table
Verified signature5026db7 -
v1.1: verified 213M fashion-vocab build (gate: 100% bit-identity on 18K texts, graceful OOV fallback)
Verified signature19b930b -
MODA Pro Lite v1.0: weights (WiSE a=0.4), config, tokenizer, card
Verified signaturecd6183f -
initial commit
Verified signature0d4bafa