Downloads · 30 days
10
20% of all-time downloads
pravsels/molmoact2_tool_removal_quantile_norm_fix_25k
molmoact2_tool_removal_quantile_norm_fix_25k is a robotics model from pravsels. 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 MolmoAct2 (action-expert-only) for toolremoval on SO101 data.
Downloads · 30 days
10
20% of all-time downloads
All-time downloads
49
Public
Parameters
5.4B
10.9 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors10.9 GB · 100%
How the weights are stored.
BF165.4B · 100%
From the Hugging Face model README
Fine-tuned MolmoAct2 (action-expert-only) for tool_removal on SO101 data.
| Policy | MolmoAct2 (policy.type=molmoact2) |
| Init checkpoint | allenai/MolmoAct2 |
| Dataset | villekuosmanen/armnetbench_tool_removal |
| Task | tool_removal |
| Action dim | 6 (single-arm) |
| Cameras | top, wrist, front |
| Training | 25k steps, QUANTILES norm, freeze, batch 32 global, Isambard GH200 |
| Prior HF repo | pravsels/molmoact2_tool_removal |
| W&B project | molmoact2_tool_removal_quantile_norm_fix_25k |
| W&B run | iq9mxnpc |
The checkpoint (local step 025000, 25k training steps) lives at the repository root for direct loading.
| Checkpoint step | 025000 |
| Source path | checkpoints/025000/pretrained_model/ |
| model.safetensors | 10,884,573,720 bytes, sha256 81df19054a6fde891b52eba8d9da5eedb7dc3e015ae77cd24811bd30f9ed10f7 |
| policy_preprocessor.json | 2,495 bytes, sha256 e7c8b8293cb0265a01f83278033272efcb21b4c7bfb031cfbd683ed74ee7b139 |
| policy_postprocessor.json | 757 bytes, sha256 6dbed1e1ec69e8c50f3a04c1f144a54231e3ef508f15fd7896ead43ea645b033 |
| train_config.json | 8,261 bytes, sha256 08931229e1a28e0ab0d111bac15c5d92ff870540c7e9e3dd1d300aec6089ea28 |
Verify after download:
sha256sum model.safetensors
# expected: 81df19054a6fde891b52eba8d9da5eedb7dc3e015ae77cd24811bd30f9ed10f7
from lerobot.policies.molmoact2.modeling_molmoact2 import MolmoAct2Policy
policy = MolmoAct2Policy.from_pretrained("pravsels/molmoact2_tool_removal_quantile_norm_fix_25k")