Downloads · 30 days
10
25% of all-time downloads
sig-autoencoder-fourier-5-cosine
maximuspowers/sig-autoencoder-fourier-5-cosine
sig-autoencoder-fourier-5-cosine 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
40
Public
Repo size
180 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt180 MB · 100%
At a glance
- Access
- Public
- Created
- Dec 11, 2025
- Updated
- Dec 11, 2025
- SHA
- 241cc739
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: cosine
- Optimizer: adam
- Learning Rate: 0.0001
- Batch Size: 16
Performance Metrics (Test Set)
- MSE: 0.299696
- MAE: 0.303521
- RMSE: 0.547445
- Cosine Similarity: 0.8642
- R² Score: 0.0638
- Created
- Dec 11, 2025
- Updated
- Dec 11, 2025