openvla-7b

# Install minimal dependencies (`torch`, `transformers`, `timm`, `tokenizers`, ...)
# > pip install -r https://raw.githubusercontent.com/openvla/openvla/main/requirements-min.txt
from transformers import AutoModelForVision2Seq, AutoProcessor
from PIL import Image

import torch

# Load Processor & VLA
processor = AutoProcessor.from_pretrained("openvla/openvla-7b", trust_remote_code=True)
vla = AutoModelForVision2Seq.from_pretrained(
    "openvla/openvla-7b",
    attn_implementation="flash_attention_2",  # [Optional] Requires `flash_attn`
    torch_dtype=torch.bfloat16, 
    low_cpu_mem_usage=True, 
    trust_remote_code=True
).to("cuda:0")

# Grab image input & format prompt
image: Image.Image = get_from_camera(...)
prompt = "In: What action should the robot take to {<INSTRUCTION>}?\nOut:"

# Predict Action (7-DoF; un-normalize for BridgeV2)
inputs = processor(prompt, image).to("cuda:0", dtype=torch.bfloat16)
action = vla.predict_action(**inputs, unnorm_key="bridge_orig", do_sample=False)

# Execute...
robot.act(action, ...)

@article{kim24openvla,
    title={OpenVLA: An Open-Source Vision-Language-Action Model},
    author={{Moo Jin} Kim and Karl Pertsch and Siddharth Karamcheti and Ted Xiao and Ashwin Balakrishna and Suraj Nair and Rafael Rafailov and Ethan Foster and Grace Lam and Pannag Sanketi and Quan Vuong and Thomas Kollar and Benjamin Burchfiel and Russ Tedrake and Dorsa Sadigh and Sergey Levine and Percy Liang and Chelsea Finn},
    journal = {arXiv preprint arXiv:2406.09246},
    year={2024}
}