pravsels's picture
Update model card
d495594 verified
|
Raw
History Blame Contribute Delete
2.22 kB
---
library_name: lerobot
tags:
- molmoact2
- robotics
- lerobot
- vla
- bimanual
base_model: allenai/MolmoAct2
---
# molmoact2_transfer_cube_quantile_norm_fix_25k
Fine-tuned [MolmoAct2](https://huggingface.co/allenai/MolmoAct2) (action-expert-only) for `transfer_cube` on SO101 data.
| | |
|---|---|
| **Policy** | MolmoAct2 (`policy.type=molmoact2`) |
| **Init checkpoint** | [allenai/MolmoAct2](https://huggingface.co/allenai/MolmoAct2) |
| **Dataset** | [villekuosmanen/armnetbench_transfer_cube](https://huggingface.co/datasets/villekuosmanen/armnetbench_transfer_cube) |
| **Task** | `transfer_cube` |
| **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_transfer_cube](https://huggingface.co/pravsels/molmoact2_transfer_cube) |
| **W&B project** | [molmoact2_transfer_cube_quantile_norm_fix_25k](https://wandb.ai/pravsels/molmoact2_transfer_cube_quantile_norm_fix_25k) |
| **W&B run** | [skd3uk47](https://wandb.ai/pravsels/molmoact2_transfer_cube_quantile_norm_fix_25k/runs/skd3uk47) |
## 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 `e577aac40c49a0783a6ff3b7b063d94408b4a48ee32d8117107ef25960b1ee73` |
| **policy_preprocessor.json** | 2,523 bytes, sha256 `aac2ee4e61c26a5322c9b3e2f727ce060c90071e012185d9f39cceb2d43ea04a` |
| **policy_postprocessor.json** | 758 bytes, sha256 `8690a8e7015281571c9de7d88073b302cd03123e5f677ea582c669dbf014e7ad` |
| **train_config.json** | 8,836 bytes, sha256 `99076bc43d5034125e205a7fa7078a0e706b4346beebf0acf53f1323a0f83b72` |
Verify after download:
```bash
sha256sum model.safetensors
# expected: e577aac40c49a0783a6ff3b7b063d94408b4a48ee32d8117107ef25960b1ee73
```
## Usage
```python
from lerobot.policies.molmoact2.modeling_molmoact2 import MolmoAct2Policy
policy = MolmoAct2Policy.from_pretrained("pravsels/molmoact2_transfer_cube_quantile_norm_fix_25k")
```