Documentation

Quick Start

# Install vlarobot
pip install vlarobot

# List available model presets
from vlarobot.models.registry import list_presets
print(list_presets())
# ['openvla-7b', 'smolvla-450m', 'dream-vla-7b']

# Load a model (requires GPU + HuggingFace weights)
from vlarobot import VLAModel
model = VLAModel.from_preset("openvla-7b")

# Predict action from image + instruction
from PIL import Image
image = Image.open("robot_view.jpg")
action = model.predict(image, "pick up the cup")
print(action)  # Action(x=0.12, y=-0.05, ...)