You can deploy this model and start earning money today!

roy-W/
ired-reasoning

Name: ired-reasoning
Availability: InStock

Views

No views yet

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

python

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'])

roy-W/ired-reasoning

IRED Autoencoder — roy-W/ired-reasoning

Usage

roy-W/
ired-reasoning

IRED Autoencoder — `roy-W/ired-reasoning`