2e9cd87bbd
* first commit * feat(policies): add VLA-JEPA * feat(policies): add VLA-JEPA * support vla_jepa * (feat)policies: add VLA-JEPA * linting * adding deps to pyproject.toml * updating uv lock * adding guards to avoid needing transformers and diffusers for type checking and basic tests * fixing action and state dim * fix warnings with qwen processor kwargs * fixing wm_loss not propagating * adjusting obs steps, tublets size to match original implementation * some more fixes to be closer to the original implem * adding more tests to ensure good coverage * align VLA-JEPA architecture with original checkpoint - Remove stale `action_num_heads` / `action_attention_head_dim` config fields; DiT head dimensions are now always derived from the preset (DiT-B/L/test). - Add `num_target_vision_tokens` and `action_max_seq_len` config fields required by the action head's future-token embedding and positional embedding tables. - Fix default `qwen_model_name` to 2B (matches all released checkpoints). - Rename `ActionEncoder` attrs w1/w2/w3 → layer1/layer2/layer3 to match checkpoint key names; replace `nn.Sequential` decoder/state-encoder with `_MLP2` (layer1/layer2 naming). - Fix `VLAJEPAActionHead` to size ActionEncoder and StateEncoder at `inner_dim` (DiT input width) rather than `action_hidden_size` (DiT output width). - Rename `DiT.blocks` → `transformer_blocks` and `attn` → `attn1` to match checkpoint; add alternating cross/self attention (even blocks cross-attend to Qwen context, odd blocks self-attend). - Add `DiT-test` preset for unit tests. - Rewrite `ActionConditionedVideoPredictor` with explicit ViT-style blocks (`_PredictorBlock` with fused qkv) to match checkpoint structure; rename `encoder`/`norm`/`proj` → `predictor_blocks`/`predictor_norm`/`predictor_proj`. * propagate action_is_pad masking through VLA-JEPA policy pipeline Pass the `action_is_pad` tensor from the batch through to the action head so padded timesteps are excluded from the flow-matching loss. * update VLA-JEPA tests for arch changes and action_is_pad - Switch conftest to use `action_model_type="DiT-test"` now that `action_num_heads` / `action_attention_head_dim` have been removed. - Add action_head tests covering fully-padded loss (zero) and equivalence of action_is_pad=None vs all-zeros mask. - Remove obsolete `test_native_to_lerobot_wm_only` test. * add VLA-JEPA documentation Covers architecture overview, pretrained checkpoints, config reference, training/eval commands for LIBERO-10, and guidance on fine-tuning for single-camera datasets. * add one-shot script to convert ginwind/VLA-JEPA checkpoints to safetensors (will remove once migrated) * make default params more aligned with paper and pretrained models - adding possibility of freezing qwen backbone and world model - added tests for weight loading * trying out to re-init the action head to avoid pretraining dimension mismatch * allow different state dim and action dim * removing missleading future_action_window_size to just use chunk_size * lots of changes to make existing weights work, need to massively refactor the pre and post processing * refactoring into using pre and post processor * pre-commit cleanup * fixing doc defaults args Signed-off-by: Maxime Ellerbach <maxime@ellerbach.net> * adressing dtype zeros issue * adding guard for diffusers * fixing training and exal examples * trying to close success rate gap * fix qwen norm layer output libero eval is now as expected * adding instructions for different embodiement + fixing some tests * smol fix to avoid having default CPU device when training * fixing misconception about multiview / singleview handling * removing conversion script * adding licences * adding .mdx docs and shortening polivy_vla_jepa_README.md * removing useless pre-processor * cleanup * removing swish in favor of silu * adding configuration gripper index and threshold * fixing simlink --------- Signed-off-by: Maxime Ellerbach <maxime@ellerbach.net> Co-authored-by: ginwind <ginwind@mail.ustc.edu.cn>
Generating the documentation
To generate the documentation, you first have to build it. Several packages are necessary to build the doc, you can install them with the following command, at the root of the code repository:
pip install -e . -r docs-requirements.txt
You will also need nodejs. Please refer to their installation page
NOTE
You only need to generate the documentation to inspect it locally (if you're planning changes and want to
check how they look before committing for instance). You don't have to git commit the built documentation.
Building the documentation
Once you have setup the doc-builder and additional packages, you can generate the documentation by
typing the following command:
doc-builder build lerobot docs/source/ --build_dir ~/tmp/test-build
You can adapt the --build_dir to set any temporary folder that you prefer. This command will create it and generate
the MDX files that will be rendered as the documentation on the main website. You can inspect them in your favorite
Markdown editor.
Previewing the documentation
To preview the docs, first install the watchdog module with:
pip install watchdog
Then run the following command:
doc-builder preview lerobot docs/source/
The docs will be viewable at http://localhost:3000. You can also preview the docs once you have opened a PR. You will see a bot add a comment to a link where the documentation with your changes lives.
NOTE
The preview command only works with existing doc files. When you add a completely new file, you need to update _toctree.yml & restart preview command (ctrl-c to stop it & call doc-builder preview ... again).
Adding a new element to the navigation bar
Accepted files are Markdown (.md).
Create a file with its extension and put it in the source directory. You can then link it to the toc-tree by putting
the filename without the extension in the _toctree.yml file.
Renaming section headers and moving sections
It helps to keep the old links working when renaming the section header and/or moving sections from one document to another. This is because the old links are likely to be used in Issues, Forums, and Social media and it'd make for a much more superior user experience if users reading those months later could still easily navigate to the originally intended information.
Therefore, we simply keep a little map of moved sections at the end of the document where the original section was. The key is to preserve the original anchor.
So if you renamed a section from: "Section A" to "Section B", then you can add at the end of the file:
Sections that were moved:
[ <a href="#section-b">Section A</a><a id="section-a"></a> ]
and of course, if you moved it to another file, then:
Sections that were moved:
[ <a href="../new-file#section-b">Section A</a><a id="section-a"></a> ]
Use the relative style to link to the new file so that the versioned docs continue to work.
For an example of a rich moved sections set please see the very end of the transformers Trainer doc.
Adding a new tutorial
Adding a new tutorial or section is done in two steps:
- Add a new file under
./source. This file can either be ReStructuredText (.rst) or Markdown (.md). - Link that file in
./source/_toctree.ymlon the correct toc-tree.
Make sure to put your new file under the proper section. If you have a doubt, feel free to ask in a Github Issue or PR.
Writing source documentation
Values that should be put in code should either be surrounded by backticks: `like so`. Note that argument names
and objects like True, None or any strings should usually be put in code.
Writing a multi-line code block
Multi-line code blocks can be useful for displaying examples. They are done between two lines of three backticks as usual in Markdown:
```
# first line of code
# second line
# etc
```
Adding an image
Due to the rapidly growing repository, it is important to make sure that no files that would significantly weigh down the repository are added. This includes images, videos, and other non-text files. We prefer to leverage a hf.co hosted dataset like
the ones hosted on hf-internal-testing in which to place these files and reference
them by URL. We recommend putting them in the following dataset: huggingface/documentation-images.
If an external contribution, feel free to add the images to your PR and ask a Hugging Face member to migrate your images
to this dataset.