VLA-OS
Official Code For VLA-OS.
File Explorer
Download Latest Version (.zip)- pertrain_vlm.sh
- train_vla.sh
- train_action_only_vla.yaml
- train_hierarchical_vla.yaml
- train_integrated_vla.yaml
- train_action_only_vla.yaml
- train_hierarchical_vla.yaml
- train_integrated_vla.yaml
- train_action_only_vla.yaml
- train_hierarchical_vla.yaml
- train_integrated_vla.yaml
- train_action_only_vla.yaml
- train_hierarchical_vla.yaml
- train_integrated_vla.yaml
- train_action_only_vla.yaml
- train_hierarchical_vla.yaml
- train_integrated_vla.yaml
- train_action_only_vla.yaml
- train_hierarchical_vla.yaml
- train_integrated_vla.yaml
- train_action_only_vla.yaml
- train_integrated_vla.yaml
- train_action_only_vla.yaml
- train_integrated_vla.yaml
- train_action_only_vla.yaml
- train_integrated_vla.yaml
- train_action_only_vla.yaml
- train_hierarchical_vla.yaml
- train_integrated_vla.yaml
- train_vlm.yaml
- overview.png
- config.json
- tokenizer.json
- tokenizer_config.json
- vocab.json
- config.json
- tokenizer.json
- tokenizer_config.json
- vocab.json
- config.json
- tokenizer.json
- tokenizer_config.json
- vocab.json
- config.json
- tokenizer.json
- tokenizer_config.json
- vocab.json
- pretrain.py
- train_vla.py
- test_rlds_dataset.py
- __init__.py
- generalized_loss.py
- __init__.cpython-310.pyc
- __init__.cpython-38.pyc
- affine.cpython-310.pyc
- affine.cpython-38.pyc
- geodesic.cpython-310.pyc
- geodesic.cpython-38.pyc
- mixture.cpython-310.pyc
- mixture.cpython-38.pyc
- path.cpython-310.pyc
- path.cpython-38.pyc
- path_sample.cpython-310.pyc
- path_sample.cpython-38.pyc
- __init__.cpython-310.pyc
- __init__.cpython-38.pyc
- schedule_transform.cpython-310.pyc
- schedule_transform.cpython-38.pyc
- scheduler.cpython-310.pyc
- scheduler.cpython-38.pyc
- __init__.py
- schedule_transform.py
- scheduler.py
- __init__.py
- affine.py
- geodesic.py
- mixture.py
- path.py
- path_sample.py
- __init__.py
- discrete_solver.py
- ode_solver.py
- riemannian_ode_solver.py
- solver.py
- utils.py
- __init__.cpython-310.pyc
- __init__.cpython-38.pyc
- categorical_sampler.cpython-310.pyc
- categorical_sampler.cpython-38.pyc
- model_wrapper.cpython-310.pyc
- model_wrapper.cpython-38.pyc
- utils.cpython-310.pyc
- utils.cpython-38.pyc
- __init__.cpython-310.pyc
- __init__.cpython-38.pyc
- manifold.cpython-310.pyc
- manifold.cpython-38.pyc
- sphere.cpython-310.pyc
- sphere.cpython-38.pyc
- torus.cpython-310.pyc
- torus.cpython-38.pyc
- utils.cpython-310.pyc
- utils.cpython-38.pyc
- __init__.py
- manifold.py
- sphere.py
- torus.py
- utils.py
- __init__.py
- categorical_sampler.py
- model_wrapper.py
- utils.py
- __init__.py
- batching_utils.py
- flow_matching_utils.py
- infinity_utils.py
- model_utils.py
- robot_utils.py
- three_d_tokenizer.py
- utils.py
- droid_utils.py
- __init__.py
- configs.py
- materialize.py
- mixtures.py
- transforms.py
- __init__.cpython-310.pyc
- __init__.cpython-38.pyc
- data_utils.cpython-310.pyc
- data_utils.cpython-38.pyc
- goal_relabeling.cpython-310.pyc
- goal_relabeling.cpython-38.pyc
- task_augmentation.cpython-310.pyc
- task_augmentation.cpython-38.pyc
- __init__.py
- data_utils.py
- goal_relabeling.py
- task_augmentation.py
- __init__.py
- dataset.py
- obs_transforms.py
- traj_transforms.py
- __init__.py
- cot_utils.py
- data_utils.py
- datasets.py
- materialize.py
- __init__.py
- base_prompter.py
- qwen_prompter.py
- __init__.py
- base_llm.py
- qwen25.py
- __init__.py
- base_vision.py
- dinosiglip_vit.py
- dinov2_vit.py
- siglip_vit.py
- __init__.py
- action_head.py
- action_only.py
- hierarchical_vla.py
- image_foresight_head.py
- integrated_vla.py
- language_planning_head.py
- low_level_action_head.py
- nn_utils.py
- ode_solver.py
- visual_planning_head.py
- __init__.py
- base_vlm.py
- qwen_vlm.py
- __init__.py
- projector.py
- __init__.py
- overwatch.py
- __init__.py
- accelerator.py
- base_strategy.py
- fsdp.py
- metrics.py
- LICENSE
- README.md
- requirements.txt
# Installation Guide
1. Get the code
git clone https://github.com/HeegerGao/VLA-OS
Downloads the entire project code from GitHub to your computer.
cd VLA-OS
Moves into the project folder you just downloaded.
2. Official Install Script
Easy RecommendedPrerequisites
- Python 3 Python is required to use pip.
pip3 install torch torchvision torchaudio
Installs the package published on PyPI directly β no need to clone the source.
pip install flash-attn --no-build-isolation
Installs the package published on PyPI directly β no need to clone the source.
After installing, open a new terminal and run the program's version command (e.g. --version) to confirm it worked.
Pulled directly from this repo's README.
3. Python
EasyPrerequisites
pip3 install torch torchvision torchaudio
Installs the package published on PyPI directly β no need to clone the source.
pip install -r requirements.txt
Installs the Python libraries listed in requirements.txt (or similar).
pip install -e .
Installs the Python libraries listed in requirements.txt (or similar).
pip install flash-attn --no-build-isolation
Installs the package published on PyPI directly β no need to clone the source.
If it runs without errors and prints output in the terminal, it worked.
Pulled directly from this repo's README.
// repository documentation
Was this content helpful?
(0 ratings)