molmoact2_open_lamp_door_quantile_norm_fix_25k

Fine-tuned MolmoAct2 (action-expert-only) for open_lamp_door on SO101 data.

Policy	MolmoAct2 (policy.type=molmoact2)
Init checkpoint	allenai/MolmoAct2
Dataset	villekuosmanen/armnetbench_open_lamp_door
Task	open_lamp_door
Action dim	12 (bimanual)
Cameras	top, left_wrist, right_wrist
Training	25k steps, QUANTILES norm, freeze, batch 32 global, Isambard GH200
Prior HF repo	pravsels/molmoact2_open_lamp_door
W&B project	molmoact2_open_lamp_door_quantile_norm_fix_25k
W&B run	zem7639k

Checkpoints

The checkpoint (local step 025000, 25k training steps) lives at the repository root for direct loading.

Verification

| Checkpoint step | 025000 | | Source path | checkpoints/025000/pretrained_model/ | | model.safetensors | 10,884,573,720 bytes, sha256 4f44153edf09cd1213578bbf8b72c33e1ee61b61d929a71a5745b366530fae53 | | policy_preprocessor.json | 2,523 bytes, sha256 aac2ee4e61c26a5322c9b3e2f727ce060c90071e012185d9f39cceb2d43ea04a | | policy_postprocessor.json | 758 bytes, sha256 8690a8e7015281571c9de7d88073b302cd03123e5f677ea582c669dbf014e7ad | | train_config.json | 8,840 bytes, sha256 cd8cf07d7ea0f895e6f26472e20f988a8037ad5843149bbdce48606c3b39bd69 |

Verify after download:

sha256sum model.safetensors
# expected: 4f44153edf09cd1213578bbf8b72c33e1ee61b61d929a71a5745b366530fae53

Usage

from lerobot.policies.molmoact2.modeling_molmoact2 import MolmoAct2Policy
policy = MolmoAct2Policy.from_pretrained("pravsels/molmoact2_open_lamp_door_quantile_norm_fix_25k")