Downloads · 30 days
20
30% of all-time downloads
vla-jepa-molmoact-yam-blocks-v2
helen9975/vla-jepa-molmoact-yam-blocks-v2
vla-jepa-molmoact-yam-blocks-v2 is a robotics model from helen9975. 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. The card lists the license as apache-2.0.
Fine-tuned VLA-JEPA on the MolmoAct2-BimanualYAM-Dataset with 3 cameras packed top → left → right, unfrozen VLM, and world-model loss on (blocksv2 recipe).
All-time downloads
66
Public
Parameters
2.8B
6.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.2 GB · 100%
Parameter types
How the weights are stored.
BF162.5B · 89%
Base models
Model card
From the Hugging Face model README
VLA-JEPA MolmoAct2 BimanualYAM (blocks_v2)
Fine-tuned VLA-JEPA on the MolmoAct2-BimanualYAM-Dataset with 3 cameras packed top → left → right, unfrozen VLM, and world-model loss on (blocks_v2 recipe).
Checkpoint details
| Setting | Value |
|---|---|
| Training step | 100000 |
| Cameras | top → left → right |
| Action dim | 14 (absolute joints + grippers) |
| Chunk size | 30 (@ 30 Hz) |
| VLM | unfrozen |
| World model | on |
| Base model | lerobot/VLA-JEPA-Pretrain |
| Gripper range | [0, 1] (continuous) |
Usage (LeRobot)
from lerobot.policies.vla_jepa.modeling_vla_jepa import VLAJEPAPolicy
from lerobot.policies.factory import make_pre_post_processors
ckpt = "helen9975/vla-jepa-molmoact-yam-blocks-v2"
policy = VLAJEPAPolicy.from_pretrained(ckpt)
preprocessor, postprocessor = make_pre_post_processors(policy.config, pretrained_path=ckpt)
Open-loop smoke (2 held-out episodes, stride 30, reset-each-step)
- MSE: 0.00672
- MAE: 0.0596
- Task
- Robotics
- Library
- lerobot
- License
- apache-2.0
- Created
- Jul 20, 2026
- Updated
- Jul 20, 2026