| --- |
| library_name: pimm |
| datasets: |
| - DeepLearnPhysics/PILArNet-M |
| tags: |
| - particle-physics |
| - lartpc |
| - point-cloud |
| --- |
| |
| # Panda — PointTransformerV3 encoder (pretrained) |
|
|
| PointTransformerV3 (`PT-v3m2`) encoder pretrained with masked point modeling on LArTPC (PILArNet) data. Backbone / warm-start for downstream tasks (no task head). |
|
|
| - **pimm type:** `PT-v3m2` · encoder-only · enc_channels (48,96,192,384,512) |
| |
| ## Loading |
| |
| ```python |
| import pimm |
| model = pimm.from_pretrained("hf://deeplearnphysics/panda-base") |
| ``` |
| |
| ## Provenance |
| |
| Repackaged from the original [`panda`](https://github.com/DeepLearnPhysics/panda) checkpoints into the [`pimm`](https://github.com/youngsm/particle-imaging-models) export format. Inherits the source repo's license. |
| |
