---
library_name: lerobot
license: apache-2.0
tags:
- robotics
- lerobot
- groot
- bimanual
- yam
- molmoact
pipeline_tag: robotics
base_model: nvidia/GR00T-N1.7-3B
datasets:
- allenai/MolmoAct2-BimanualYAM-Dataset
---

# GR00T N1.7 MolmoAct2 BimanualYAM

Partial fine-tune of [GR00T N1.7](https://huggingface.co/nvidia/GR00T-N1.7-3B) on the [MolmoAct2-BimanualYAM-Dataset](https://huggingface.co/datasets/allenai/MolmoAct2-BimanualYAM-Dataset) (3 cameras: top → left → right). Projector + diffusion trainable; LLM/vision frozen.

## Checkpoint details

| Setting | Value |
|---------|-------|
| Training step | 30000 |
| Cameras | top, left, right |
| Action dim | 14 (absolute joints + grippers) |
| Chunk size | 16 |
| Embodiment | new_embodiment |
| Base model | nvidia/GR00T-N1.7-3B |
| Gripper range | [0, 1] (continuous) |

## Usage (LeRobot)

```python
from lerobot.policies.groot.modeling_groot import GrootPolicy
from lerobot.policies.factory import make_pre_post_processors

ckpt = "helen9975/groot-n1.7-molmoact-yam"
policy = GrootPolicy.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:** 0.00160
- **MAE:** 0.0244