---
title: MaskWAM-libero-ckpt
canonical_url: "https://www.modelscope.ai/models/hanyangyu1021/MaskWAM-libero-ckpt"
md_url: "https://www.modelscope.ai/models/hanyangyu1021/MaskWAM-libero-ckpt.md"
repository: hanyangyu1021/MaskWAM-libero-ckpt
last_updated: 2026-10-13
license: apache-2.0
base_model:
  - Wan-AI/Wan2.2-TI2V-5B
base_model_relation: finetune
parameters: 5.6B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 48
stars: 0
---

# MaskWAM-libero-ckpt

> MaskWAM-libero-ckpt - An open-source model by hanyangyu1021 on ModelScope. MaskWAM LIBERO Checkpoint

hanyangyu1021/MaskWAM-libero-ckpt is a 5.6B-parameter machine learning model on ModelScope. licensed under apache-2.0. derived from Wan-AI/Wan2.2-TI2V-5B.

- **Repository**: hanyangyu1021/MaskWAM-libero-ckpt
- **License**: apache-2.0
- **Parameters**: 5.6B
- **Base model**: Wan-AI/Wan2.2-TI2V-5B
- **Downloads**: 48
- **Stars**: 0
- **Last updated**: 2026-10-13

Source: https://www.modelscope.ai/models/hanyangyu1021/MaskWAM-libero-ckpt

---

# MaskWAM LIBERO Checkpoint

This is the LIBERO simulation checkpoint for
[MaskWAM](https://github.com/hanyangyu1021/maskwam).

The checkpoint uses:

- model type: `mask_wan_mot_sim`
- image size: `384 × 320`
- action chunk: 48 steps
- `input_mask=false`
- future RGB and mask prediction

## Files

- `config.json`: model architecture and inference configuration
- `model.safetensors`: MaskWAM policy weights

WAN2.2 and LIBERO are external dependencies. Evaluation must use the released
normalization statistics from
[MaskWAM-libero](https://www.modelscope.ai/datasets/hanyangyu1021/MaskWAM-libero/tree/master/libero_vam).

## License

This checkpoint contains weights derived from
[Wan2.2-TI2V-5B](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B)
and is distributed under the Apache License 2.0. The MaskWAM source code is
distributed separately under the MIT License. See `LICENSE` for the checkpoint
license terms.

## Download

```bash
pip install -U modelscope-hub

ms download hanyangyu1021/MaskWAM-libero-ckpt \
  --local-dir "$MASKWAM_CHECKPOINT_ROOT/MaskWAM-libero-ckpt"

ms download hanyangyu1021/MaskWAM-libero \
  libero_vam/qpos_mean_std_online.pkl \
  --repo-type dataset \
  --local-dir "$MASKWAM_DATA_ROOT"
```

## Evaluate

```bash
export LIBERO_ROOT=/path/to/LIBERO
export MASKWAM_WAN_PATH=/path/to/Wan2.2-TI2V-5B

scripts/eval_libero.sh \
  --task_suite libero_spatial \
  --num_trials 50
```

The default evaluation paths resolve to the downloaded checkpoint and
normalization file through `MASKWAM_CHECKPOINT_ROOT` and `MASKWAM_DATA_ROOT`.