Instructions to use yuchen0187/RegressionPolicy-Cosmos with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Cosmos
How to use yuchen0187/RegressionPolicy-Cosmos with Cosmos:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
RegressionPolicy-Cosmos
HT checkpoint for LIBERO-10: libero_10/iter_000002000 (nu=640).
Native PyTorch distributed model checkpoint; retain all eight model shards and .metadata.
Action statistics are in libero_10/action_stats.json; the matching VAE is in
assets/wan22_vae/Wan2.2_VAE.pth. Use the matching HT-capable Cosmos runtime.
Built on NVIDIA Cosmos. The checkpoint uses upstream OpenMDW-1.1, included in LICENSE. These license obligations come from the upstream model, not additional restrictions imposed by the RegressionPolicy authors. The VAE has its own Apache-2.0 license. See NOTICE for attribution and modifications.
- Downloads last month
- -
Model tree for yuchen0187/RegressionPolicy-Cosmos
Base model
nvidia/Cosmos3-Nano