← Back to Architecture

JEPA encoder-decoder

Architecture
Used in
1 PRs
Best BPB
1.2622
Avg BPB
1.2622

Hyperparameters Across PRs

pr_numberparameters
696{"encoder_layers":5,"encoder_repeats":2,"decoder_layers":7,"model_dim":480,"encoder_heads":6,"encoder_kv_heads":3,"decoder_heads":4,"patch_size":8,"latent_dim":192}