metadata
library_name: ired
tags:
- autoencoder
- bart
- latent-diffusion
IRED Autoencoder — roy-W/ired-reasoning
Frozen BART autoencoder with compression/reconstruction split.
- Pool type:
conv - Latent slots (K): 384
- d_ae: 768
- Decoder fine-tuned: yes
- Base model:
facebook/bart-base - Training steps: 5
Usage
from ired.model.autoencoder import FrozenBartAutoencoder
import torch
ae = FrozenBartAutoencoder(
model_name='facebook/bart-base',
k=384,
pool_type='conv',
d_ae=768,
train_decoder=True,
)
ckpt = torch.load('ae_checkpoint.pt', map_location='cpu')
ae.load_ae(ckpt['ae'])