# OpenVLA-Micro

Small-vision VLA for CPU robot deployment — trained on LIBERO-90.

This repo is structured so it can be used as a plain source checkout, a Python package, or a Hugging Face model/code bundle. Large weight files are meant to stay out of GitHub history and be hosted separately when needed.

| Component | Detail |
|-----------|--------|
| Vision | DINOv2-S (384d, 256 patches) + SigLIP-B/16 (768d, 196 patches) |
| Projector | ShimMLP(384→2048→8704) + ShimMLP(768→2048→8704) → Concat → Linear(8704→896) → GELU → Linear(896→896) |
| LLM | Qwen2.5-0.5B (896 hidden, 151k vocab, 256 extra tokens) |
| Action | 7-DoF, discretized into 256 bins per dim, minmax de-normalization |
| Trainable | 38.1M params (shim MLPs + LoRA rank 8 on projector) |
| Frozen | DINOv2, SigLIP, Qwen2.5 (all layers + lm_head + embed_tokens) |
| Training | 5000 steps, batch 64, LR 2e-4 w/ 200-step warmup → cosine to 1e-5 |

## Inference

Install as a package:

```bash
pip install -e .
```

Run the CLI:

```bash
openvla-micro --checkpoint openvla-micro-merged.pt --image demo.jpg "pick up the red block"
```

```python
from PIL import Image
from modeling_openvla_micro import OpenVLAMicro

model = OpenVLAMicro.from_pretrained("openvla-micro-merged.pt", device="cpu")
model.eval()

image = Image.open("demo.jpg").convert("RGB")
action = model.predict_action(image, "pick up the red block")
print(action)  # [dx, dy, dz, droll, dpitch, dyaw, gripper]
```

The checkpoint argument can also be a Hugging Face repo ID if that repo contains `openvla-micro-merged.pt` or `openvla-micro-distill.pt`.

## Data

Checkpoint includes normalization statistics for the following dataset:

- `libero_90`: 7-DoF end-effector deltas, 256-bin tokenization

## Citation

Built on [openvla-mini](https://github.com/openvla/openvla-mini) and [MiniVLA](https://github.com/rail-berkeley/TinyVLA).

```
@misc{openvla-micro-2026,
  author = {},
  title = {OpenVLA-Micro: Small-vision VLA for CPU Robot Deployment},
  year = {2026},
}
```