You need to agree to share your Hugging Face information to access this model
This repository is publicly accessible, but you have to accept the conditions to access its files and content.
Access to this checkpoint is granted manually by the authors.
Log in or Sign Up to review the conditions and access this model content.
agwam1
A fine-tuned checkpoint of OpenWAM-Alpha-Sim-LIBERO (OpenWAM-α, 12.4B parameters, bf16) for the LIBERO simulation benchmark. Training and evaluation details are not included here yet.
Files
| File | Description |
|---|---|
checkpoint_step_8192.safetensors |
Weights, 24.8 GB, bf16 (file name follows OpenWAM's checkpoint_step_<micro-step> convention) |
config.yaml |
Model config, identical to OpenWAM-Alpha-Sim-LIBERO |
normalization_stats.npy |
Action normalization statistics, identical to OpenWAM-Alpha-Sim-LIBERO |
tokenizer/ |
umt5-xxl tokenizer, identical to OpenWAM-Alpha-Sim-LIBERO |
l1/ |
A second checkpoint from the same base, as a self-contained checkpoint directory (checkpoint_step_8192.safetensors, config.yaml, normalization_stats.npy, tokenizer/) |
SHA256SUMS |
sha256 of every file |
LICENSE-OpenWAM |
Apache-2.0 license of the OpenWAM base model |
Usage
Use it like OpenWAM-Alpha-Sim-LIBERO: pass the downloaded directory to OpenWAM's deployment / evaluation code as the checkpoint directory. Downloading needs an approved access request and a Hugging Face token.
hf download Nikonikoni666/agwam1 --local-dir agwam1 --token <your token>
cd agwam1 && sha256sum -c SHA256SUMS
The root directory is one checkpoint directory and l1/ is another. To download only one of them, add --exclude "l1/*" or --include "l1/*".
Acknowledgement
Based on OpenWAM (Apache-2.0, see LICENSE-OpenWAM).
@article{wang2026openwam,
title = {OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining},
author = {Yuran Wang and Siqiao Huang and Mingleyang Li and Chenhao Zhang and Jiaqi Liang and Weiyang Jin and Yue Chen and Xuemin Chi and Donghao Zhou and Qize Yu and Yu-Kai Wang and Yuhan Rui and Shenzhe Yao and Zhen Yuan and Zhenhao Shen and Kefei Zhu and Zijie Zhu and Ning Gao and Xiaowei Chi and Guanqi He and Shanghang Zhang and Hao Dong and Lin Shao and Hang Zhao},
year = {2026},
journal = {arXiv preprint arXiv: 2609.07398}
}
- Downloads last month
- 2