Update concise Chinese model card
Browse files
README.md
CHANGED
|
@@ -1,33 +1,63 @@
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
- robotics
|
|
|
|
| 4 |
- robotwin
|
| 5 |
- safetensors
|
| 6 |
datasets:
|
|
|
|
| 7 |
- FreDERicia/SWAM-Posttrain
|
| 8 |
---
|
| 9 |
|
| 10 |
-
# SWAM
|
| 11 |
|
| 12 |
-
|
| 13 |
|
| 14 |
-
|
| 15 |
-
| --- | --- | --- |
|
| 16 |
-
| `pretrain/` | 25-4 pretraining, global step 80,000 | Embodied-model storage; initialization checkpoint for the posttraining run below |
|
| 17 |
-
| `posttrain/` | 25-4 RoboTwin Clean posttraining, global step 12,000 | DNA evaluation checkpoint |
|
| 18 |
|
| 19 |
-
|
| 20 |
|
| 21 |
-
|
| 22 |
|
| 23 |
-
|
|
|
|
|
|
|
|
|
|
| 24 |
|
| 25 |
-
|
| 26 |
-
- Pretraining data: [FreDERicia/SWAM-Pretrain](https://huggingface.co/datasets/FreDERicia/SWAM-Pretrain)
|
| 27 |
-
- Existing project code: [shaaaaron/SWAM](https://github.com/shaaaaron/SWAM)
|
| 28 |
|
| 29 |
-
##
|
| 30 |
|
| 31 |
-
|
| 32 |
|
| 33 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
- robotics
|
| 4 |
+
- world-action-models
|
| 5 |
- robotwin
|
| 6 |
- safetensors
|
| 7 |
datasets:
|
| 8 |
+
- FreDERicia/SWAM-Pretrain
|
| 9 |
- FreDERicia/SWAM-Posttrain
|
| 10 |
---
|
| 11 |
|
| 12 |
+
# SWAM
|
| 13 |
|
| 14 |
+
[](https://char-lotte-xia.github.io/swam-official/)
|
| 15 |
|
| 16 |
+
[项目主页](https://char-lotte-xia.github.io/swam-official/) · [论文](https://arxiv.org/abs/2611.12870) · [GitHub](https://github.com/shaaaaron/SWAM)
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
+
本仓库提供 **SWAM — Scaling World Action Models with Cross-Modal Alignment** 的预训练权重与 RoboTwin 后训练权重。
|
| 19 |
|
| 20 |
+
## 模型权重
|
| 21 |
|
| 22 |
+
| 权重 | 下载目录 |
|
| 23 |
+
| --- | --- |
|
| 24 |
+
| 预训练模型 | [pretrain](https://huggingface.co/FreDERicia/SWAM/tree/main/pretrain) |
|
| 25 |
+
| RoboTwin 后训练模型 | [posttrain](https://huggingface.co/FreDERicia/SWAM/tree/main/posttrain) |
|
| 26 |
|
| 27 |
+
后训练模型以上述预训练权重初始化,使用 RoboTwin Clean 数据训练。每份权重约 **27.98 GB**,以 Safetensors 分片存储。
|
|
|
|
|
|
|
| 28 |
|
| 29 |
+
## 下载与使用
|
| 30 |
|
| 31 |
+
安装 Hugging Face CLI。仓库当前为 private,下载前需使用具备访问权限的账号登录。
|
| 32 |
|
| 33 |
+
```bash
|
| 34 |
+
pip install -U huggingface_hub
|
| 35 |
+
hf auth login
|
| 36 |
+
|
| 37 |
+
# 下载预训练权重
|
| 38 |
+
hf download FreDERicia/SWAM --include "pretrain/*" --local-dir ./SWAM
|
| 39 |
+
|
| 40 |
+
# 下载后训练权重
|
| 41 |
+
hf download FreDERicia/SWAM --include "posttrain/*" --local-dir ./SWAM
|
| 42 |
+
```
|
| 43 |
+
|
| 44 |
+
训练与评测入口见 [SWAM 代码仓库](https://github.com/shaaaaron/SWAM)。使用时需将加载配置中的资源路径改为本地路径,并准备所需的 Wan/UMT5 组件;这些外部资源未包含在本仓库中。
|
| 45 |
+
|
| 46 |
+
## 配套数据
|
| 47 |
+
|
| 48 |
+
[预训练数据](https://huggingface.co/datasets/FreDERicia/SWAM-Pretrain) · [后训练数据](https://huggingface.co/datasets/FreDERicia/SWAM-Posttrain)
|
| 49 |
+
|
| 50 |
+
## 引用
|
| 51 |
+
|
| 52 |
+
如果本项目对你的研究有帮助,请引用 SWAM 论文。
|
| 53 |
+
|
| 54 |
+
```bibtex
|
| 55 |
+
@misc{zhou2026swam,
|
| 56 |
+
title = {SWAM: Scaling World Action Models with Cross-Modal Alignment},
|
| 57 |
+
author = {Yu Zhou and Xinyuan Xia and Xuankun Yang and Yinghao Yang and Wendi Chen and Bowen Liu and Jianhan Ma and Weicheng Duan and Jun Lv and Cewu Lu and Yanwei Li},
|
| 58 |
+
year = {2026},
|
| 59 |
+
eprint = {2611.12870},
|
| 60 |
+
archivePrefix = {arXiv},
|
| 61 |
+
url = {https://arxiv.org/abs/2611.12870}
|
| 62 |
+
}
|
| 63 |
+
```
|