Downloads · 30 days
7
8% of all-time downloads
smolvla_cube_in_box_v2
denys1912/smolvla_cube_in_box_v2
smolvla_cube_in_box_v2 is a robotics model from denys1912. Use it for the robotics task on the model card, and read the license before you ship it in a product. It is set up for lerobot.
SmolVLA for the SO-101 arm, task "put the cube in the box". The root of this repository holds run4's weights (object positions 1 and 2), so that --policy.path=denys1912/smolvlacubeinboxv2 keeps working unchanged.
All-time downloads
86
Public
Parameters
450M
1.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors907 MB · 100%
Parameter types
How the weights are stored.
BF16447M · 99%
Base models
Model card
From the Hugging Face model README
smolvla_cube_in_box_v2 — current model
SmolVLA for the SO-101 arm, task "put the cube in the box". The root of this
repository holds run4's weights (object positions 1 and 2),
so that --policy.path=denys1912/smolvla_cube_in_box_v2 keeps working unchanged.
Each experiment lives in its own repository: LeRobot loads config.json from the
repo root only and cannot read subfolders, so filing the runs into folders inside
one repository would make them unloadable.
| run | data | best checkpoint | val loss |
|---|---|---|---|
| run5 | 166 episodes, four positions, stratified split | step 1500 | 0.17636 |
| run4 ← the weights in root | 86 episodes, positions 1–2, stratified split | step 1250 | 0.16032 |
| run2 | 47 episodes, position 1 only | step 750 | 0.15922 |
The val losses are not comparable across runs: each holds out a different set of episodes (7 at one position, 13 across two, 25 across four). A higher number for a later run reflects a broader validation set, not a worse model.
Training code:
github.com/denysk19/vla_training — a
custom loop over LeRobot components with the held-out validation that
lerobot-train does not have at all.
- Task
- Robotics
- Library
- lerobot
- Created
- Aug 7, 2026
- Updated
- Aug 16, 2026