---
library_name: lerobot
tags:
- molmoact2
- robotics
- lerobot
- vla
base_model: allenai/MolmoAct2
---

# molmoact2_cable_unclip

Fine-tuned [MolmoAct2](https://huggingface.co/allenai/MolmoAct2) (action-expert-only) on SO101 data.

| | |
|---|---|
| **Base model** | [allenai/MolmoAct2](https://huggingface.co/allenai/MolmoAct2) |
| **Dataset** | [pravsels/cable_unclip_remote](https://huggingface.co/datasets/pravsels/cable_unclip_remote) |
| **Task** | `cable_unclip` |
| **Training** | Vast.ai H100 SXM, batch 64, bf16, gradient checkpointing |
| **W&B project** | [molmoact2_cable_unclip](https://wandb.ai/pravsels/molmoact2_cable_unclip) |
| **W&B run** | [is0gukiv](https://wandb.ai/pravsels/molmoact2_cable_unclip/runs/is0gukiv) |

## Checkpoints

| Step | Path |
|------|------|
| 006000 | `checkpoints/006000/pretrained_model/` |
| 004000 | `checkpoints/004000/pretrained_model/` |

## Usage

```python
from lerobot.policies.molmoact2.modeling_molmoact2 import MolmoAct2Policy
policy = MolmoAct2Policy.from_pretrained("pravsels/molmoact2_cable_unclip", revision="main")
```