Downloads · 30 days
17
7% of all-time downloads
fusionuncertaintynet-checkpoints
bhumika-tewari-282006/fusionuncertaintynet-checkpoints
fusionuncertaintynet-checkpoints is a machine learning model from bhumika-tewari-282006. 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 mit.
Demo checkpoint (random init, not trained) for wiring test.
All-time downloads
249
Public
Repo size
219 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin9.1 MB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Aug 24, 2026
- Updated
- Aug 28, 2026
- SHA
- 3a146590
Model card
From the Hugging Face model README
FusionUncertaintyNet Checkpoint
Demo checkpoint (random init, not trained) for wiring test.
- Architecture: AdaptiveFusion (ESM2 1280->512, ProtT5 1024->512, AF7->512) + EDR (512->512->256->128) -> Gamma(k,theta)
- Training: Kaggle P100, AdamW 1e-4, Cosine, AMP, grad_accum 2, batch_hint 16
- Loss: L = MSE + 0.5NLL_Gamma + 0.1Ramachandran
- Will be replaced by real AFdb training (501k)
Use: FusionUncertaintyNet.from_pretrained("bhumika-tewari-282006/fusionuncertaintynet-checkpoints")
- License
- mit
- Created
- Aug 24, 2026
- Updated
- Aug 28, 2026