---
title: MTV-large-patch16-256
canonical_url: "https://www.modelscope.cn/models/jtzhao2000/MTV-large-patch16-256"
md_url: "https://www.modelscope.cn/models/jtzhao2000/MTV-large-patch16-256.md"
repository: jtzhao2000/MTV-large-patch16-256
last_updated: 2026-08-17
license: apache-2.0
pipeline_tag: multi-modal-embedding
tasks:
  - multi-modal-embedding
model_type:
  - siglip
architectures:
  - SiglipModel
parameters: 652.2M
tensor_type:
  - F32
library_name:
  - safetensors
downloads: 9
stars: 0
---

# MTV-large-patch16-256

> MTV-large-patch16-256 - jtzhao2000 在 ModelScope 开源的模型。Revisiting Multi-Task Visual Representation Learning

jtzhao2000/MTV-large-patch16-256 是 ModelScope 魔搭社区上的 652.2M 参数multi-modal-embedding模型，采用 apache-2.0 许可。

- **Repository**: jtzhao2000/MTV-large-patch16-256
- **License**: apache-2.0
- **Tasks**: multi-modal-embedding
- **Parameters**: 652.2M
- **Downloads**: 9
- **Stars**: 0
- **Last updated**: 2026-08-17

Source: https://www.modelscope.cn/models/jtzhao2000/MTV-large-patch16-256

---

Revisiting Multi-Task Visual Representation Learning

https://github.com/Becomebright/MTV