| --- |
| title: OpenWAM |
| emoji: ⚡ |
| colorFrom: red |
| colorTo: blue |
| sdk: static |
| pinned: false |
| --- |
| |
| <div align="center"> |
|
|
| <img src="https://cdn-avatars.huggingface.co/v1/production/uploads/66b06fe4ce2224a4d066cc0a/MC1miu9IBqK10GW6htytf.png" width="110" alt="OpenWAM"/> |
|
|
| <h1>A Modular Open-Source Framework for Systematic Training, Inference, and Deployment of World-Action Models</h1> |
|
|
| [](https://arxiv.org/abs/XXXX.XXXXX) |
| [](https://github.com/knightnemo/OpenWAM) |
| [](https://YOUR-PROJECT-PAGE) |
| [](https://www.apache.org/licenses/LICENSE-2.0) |
|
|
| </div> |
|
|
| ## 📦 Huggingface Collections |
|
|
| - 🔬 [**OpenWAM-Study**](https://huggingface.co/collections/OpenWAM/openwam-study): Public Release of checkpoints from our controlled study on WAM design principles. |
|
|
| - 🚀 [**OpenWAM-Alpha**](https://huggingface.co/collections/YOUR-ORG/openwam-alpha): Public Release of our pretrained checkpoint (**OpenWAM-Alpha**), plus finetuned variants across downstream benchmarks. |
|
|