RoboColosseum Checkpoints
Collection
5 items β’ Updated
Οβ.β MolmoAct2 BimanualYAM
Fine-tuned Οβ.β on the MolmoAct2-BimanualYAM-Dataset (3 cameras: top β left β right).
Checkpoint details
| Setting | Value |
|---|---|
| Training step | 100000 |
| Cameras | top, left, right |
| Action dim | 14 (absolute joints + grippers) |
| Chunk size | 30 (@ 30 Hz) |
| VLM | unfrozen (freeze_vision_encoder=false, train_expert_only=false) |
| Base model | lerobot/pi05_base |
| Gripper range | [0, 1] (continuous) |
Usage (LeRobot)
from lerobot.policies.pi05.modeling_pi05 import PI05Policy
from lerobot.policies.factory import make_pre_post_processors
ckpt = "Jiafei1224/molmoact2-yam-pi05"
policy = PI05Policy.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: 0.00140
- MAE: 0.0211
- Downloads last month
- 57