Downloads · 30 days
18
11% of all-time downloads
VLA-JEPA-SO101-30
coltonhabr/VLA-JEPA-SO101-30
VLA-JEPA-SO101-30 is a robotics model from coltonhabr. 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.
Fine-tuned VLA-JEPA policy for an SO-101 pick-and-place task:
All-time downloads
157
Public
Parameters
2.3B
4.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.9 GB · 100%
Parameter types
How the weights are stored.
BF162.1B · 93%
Base models
Model card
From the Hugging Face model README
VLA-JEPA-SO101-30
Fine-tuned VLA-JEPA policy for an SO-101 pick-and-place task:
Pick up the black cube and place it in the green outlined square.
Training
- Base model:
lerobot/VLA-JEPA-Pretrain - Dataset: local
so101_black_cube_green_square_30 - Episodes: 30 teleoperated runs
- Steps: 5,000
- Batch size: 1
- Hardware: NVIDIA A10G
- Runtime: 32m48s
- Hub push during training: disabled
The training run used the SO-101 6D state/action space. The VLA-JEPA action/state adapter tensors were reinitialized to match that dimensionality.
Loading
From a compatible LeRobot checkout:
uv run lerobot-eval \
--policy.path=coltonhabr/VLA-JEPA-SO101-30
For training or evaluation pipelines that use the original dataset camera keys, apply the same rename map used during fine-tuning:
rename_map:
observation.images.top: observation.images.exterior_1_left
observation.images.wrist: observation.images.exterior_2_left
- Task
- Robotics
- Library
- lerobot
- Created
- Jun 10, 2026
- Updated
- Jun 10, 2026