Downloads · 30 days
0
vit-beatrix-contrarian
AbstractPhil/vit-beatrix-contrarian
vit-beatrix-contrarian is a machine learning model from AbstractPhil. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
- Type: wide - Total Parameters: 111,505,532 - Towers: 16 (8 pos/neg pairs) - Embed Dim: 512 - Depth: 2 layers per tower
Access
Public
Updated Dec 29, 2025
Repo size
15.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth8.8 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Dec 29, 2025
- Updated
- Dec 29, 2025
- SHA
- f95e27a3
Model card
From the Hugging Face model README
ViT-Beatrix V5 Contrarian Tower Collective
Run: v5_wide_20251229_051425
Model Configuration
- Type: wide
- Total Parameters: 111,505,532
- Towers: 16 (8 pos/neg pairs)
- Embed Dim: 512
- Depth: 2 layers per tower
Training Progress (Epoch 100)
- Test Accuracy: 55.94%
- Best Accuracy: 56.13%
Files
v5_wide_20251229_051425_best.pth- Best checkpointv5_wide_20251229_051425_e*.pth- Interval checkpointstensorboard/- Training metrics
Usage
There is no streamlined way to use this model yet, however the trainer is present with the necessary implications to load and use it.
- License
- apache-2.0
- Created
- Dec 29, 2025
- Updated
- Dec 29, 2025