Downloads · 30 days
3
9% of all-time downloads
sig-autoencoder-fourier-5-simclr-mse
maximuspowers/sig-autoencoder-fourier-5-simclr-mse
sig-autoencoder-fourier-5-simclr-mse is a machine learning model from maximuspowers. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model is a weight-space autoencoder trained on neural network activation weights/signatures. It includes both an encoder (compresses weights into latent representations) and a decoder (reconstructs weights from l…
All-time downloads
32
Public
Repo size
181 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt180 MB · 99%
At a glance
- Access
- Public
- Created
- Dec 11, 2025
- Updated
- Dec 13, 2025
- SHA
- 03f5c887
Datasets
Model card
From the Hugging Face model README
Weight-Space Autoencoder (TRANSFORMER)
This model is a weight-space autoencoder trained on neural network activation weights/signatures. It includes both an encoder (compresses weights into latent representations) and a decoder (reconstructs weights from latent codes).
Model Description
- Architecture: Transformer encoder-decoder
- Training Dataset: maximuspowers/muat-fourier-5
- Input Mode: signature
- Latent Dimension: 256
Tokenization
- Chunk Size: 64 weight values per token
- Max Tokens: 512
- Metadata: True
Training Config
- Loss Function: contrastive
- Optimizer: adam
- Learning Rate: 0.0001
- Batch Size: 8
Performance Metrics (Test Set)
- MSE: 0.088272
- MAE: 0.213148
- RMSE: 0.297107
- Cosine Similarity: 0.8509
- R² Score: 0.7242
- Created
- Dec 11, 2025
- Updated
- Dec 13, 2025