Downloads · 30 days
0
ibl-bwb-nuclr
nerdslab/ibl-bwb-nuclr
ibl-bwb-nuclr is a machine learning model from nerdslab. 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 pytorch. The card lists the license as mit.
Contrastive pretraining on single-unit features, over 57,487 IBL Neuropixels units. Five seeds, each with the unit embeddings it produces, for brain-region decoding (TS3). 10.5M parameters per checkpoint.
Access
Public
Updated Sep 21, 2026
Repo size
1.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt1.4 GB · 100%
At a glance
- Library
- pytorch
- License
- mit
- Access
- Public
- Created
- Sep 12, 2026
- Updated
- Sep 21, 2026
- SHA
- e12eb2a7
Model card
From the Hugging Face model README
NuCLR · IBL BrainWideBench
Contrastive pretraining on single-unit features, over 57,487 IBL Neuropixels units. Five seeds, each with the unit embeddings it produces, for brain-region decoding (TS3). 10.5M parameters per checkpoint.
hf download nerdslab/ibl-bwb-nuclr nuclr_embeddings_42.pt --local-dir embs
python src/ts3/eval.py probe=mlp emb_path=embs/nuclr_embeddings_42.pt
Seeds 42 to 46, as nuclr_<seed>.pt and nuclr_embeddings_<seed>.pt.
Loading a checkpoint with torch.load needs weights_only=False, since it carries its
run config alongside the weights.
Paper · Benchmark · Docs · Leaderboard · Training runs
- Library
- pytorch
- License
- mit
- Created
- Sep 12, 2026
- Updated
- Sep 21, 2026