---
title: VL-SAE
canonical_url: "https://www.modelscope.cn/models/ssfgunner/VL-SAE"
md_url: "https://www.modelscope.cn/models/ssfgunner/VL-SAE.md"
repository: ssfgunner/VL-SAE
last_updated: 2025-10-10
license: "Apache License 2.0"
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
library_name:
  - pytorch
frameworks:
  - Pytorch
downloads: 3
stars: 0
---

# VL-SAE

> VL-SAE - ssfgunner 在 ModelScope 开源的模型。Sparse Autoencoder for Vision-Language Models.

ssfgunner/VL-SAE 是 ModelScope 魔搭社区上的image-text-to-text模型，采用 Apache License 2.0 许可。

- **Repository**: ssfgunner/VL-SAE
- **License**: Apache License 2.0
- **Tasks**: image-text-to-text
- **Downloads**: 3
- **Stars**: 0
- **Last updated**: 2025-10-10

Source: https://www.modelscope.cn/models/ssfgunner/VL-SAE

---

This repository is the pre-trained weights and metadata of [VL-SAE](https://github.com/ssfgunner/VL-SAE).

Download using SDK
```bash
#Install ModelScope
pip install modelscope
```
```python
from modelscope import snapshot_download
model_dir = snapshot_download('ssfgunner/VL-SAE')
```
Download using Git
```
git clone https://www.modelscope.cn/ssfgunner/VL-SAE.git
```