Downloads · 30 days
5
11% of all-time downloads
ired-reasoning
roy-W/ired-reasoning
ired-reasoning is a machine learning model from roy-W. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for ired.
Frozen BART autoencoder with compression/reconstruction split.
All-time downloads
44
Public
Repo size
2.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt1.7 GB · 100%
At a glance
- Library
- ired
- Access
- Public
- Created
- May 28, 2026
- Updated
- May 31, 2026
- SHA
- 604f8001
Model card
From the Hugging Face model README
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'])
- Library
- ired
- Created
- May 28, 2026
- Updated
- May 31, 2026