Instructions to use knightnemo/vam-actionmot-openwam-backbone with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Wan2.2
How to use knightnemo/vam-actionmot-openwam-backbone with Wan2.2:
# 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
VAM OpenWAM ActionMoT Backbone
FastWAM-style preprocessed OpenWAM ActionMoT backbone payload generated from local Wan2.2-TI2V-5B video DiT shards.
File: ActionMoT_openwam_linear_interp_Wan22_alphascale_1024hdim.pt
Policy:
- fp32 payload storage
- sequential 1D linear interpolation with
align_corners=True - alpha scaling when the last dimension changes
- action embedding/head and proprio-specific params are excluded and remain randomly initialized by the training code
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support