The images are resized and then encoded with the DC-AE f32 autoencoder. The resizing is done with a bucketmanager with base resolution 512x512, minimum side length 256, maximum side length 1024, all sides are divisible by 32 ofcourse as they needed to be encoded by the DCAEf32 encoder. The captions are generated with moondream2, encoded with siglip and bert. (Bert embeddings variance is very high, so use a norm layer). The text embeddings are padded to 64 tokens, but i have provided the… See the full description on the dataset page: https://huggingface.co/datasets/SwayStar123/preprocessed_commoncatalog-cc-by_DCAE.
Use this model
Pull with QuantumShield
quantumshield pull SwayStar123/preprocessed_commoncatalog-cc-by_DCAE Verify integrity
quantumshield verify SwayStar123/preprocessed_commoncatalog-cc-by_DCAE pip install
pip install quantumshield && quantumshield pull SwayStar123/preprocessed_commoncatalog-cc-by_DCAE Unverified Model
This model has not been PQC-verified. File integrity cannot be guaranteed against quantum threats.
README.md
preprocessed_commoncatalog-cc-by_DCAE
The images are resized and then encoded with the DC-AE f32 autoencoder. The resizing is done with a bucketmanager with base resolution 512x512, minimum side length 256, maximum side length 1024, all sides are divisible by 32 ofcourse as they needed to be encoded by the DCAEf32 encoder. The captions are generated with moondream2, encoded with siglip and bert. (Bert embeddings variance is very high, so use a norm layer). The text embeddings are padded to 64 tokens, but i have provided the… See the full description on the dataset page: https://huggingface.co/datasets/SwayStar123/preprocessed_commoncatalog-cc-by_DCAE.
Intended Uses
This model is registered on the QuantaMrkt quantum-safe registry. This model has not yet been PQC-verified.
Quick Start
# Install the CLI pip install quantumshield # Pull the model quantumshield pull SwayStar123/preprocessed_commoncatalog-cc-by_DCAE # Verify file integrity quantumshield verify SwayStar123/preprocessed_commoncatalog-cc-by_DCAE
About
The images are resized and then encoded with the DC-AE f32 autoencoder. The resizing is done with a bucketmanager with base resolution 512x512, minimum side length 256, maximum side length 1024, all sides are divisible by 32 ofcourse as they needed to be encoded by the DCAEf32 encoder. The captions are generated with moondream2, encoded with siglip and bert. (Bert embeddings variance is very high, so use a norm layer). The text embeddings are padded to 64 tokens, but i have provided the… See the full description on the dataset page: https://huggingface.co/datasets/SwayStar123/preprocessed_commoncatalog-cc-by_DCAE.
Get this model
Pull with QuantumShield
quantumshield pull SwayStar123/preprocessed_commoncatalog-cc-by_DCAE Verify signatures
quantumshield verify SwayStar123/preprocessed_commoncatalog-cc-by_DCAE