---
title: clip-flant5-xxl
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/clip-flant5-xxl"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/clip-flant5-xxl.md"
repository: AI-ModelScope/clip-flant5-xxl
last_updated: 2024-12-23
license: apache-2.0
model_type:
  - t5
architectures:
  - CLIPT5ForConditionalGeneration
library_name:
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 58226
stars: 1
---

# clip-flant5-xxl

> clip-flant5-xxl - AI-ModelScope 在 ModelScope 开源的模型。CLIP-FlanT5-XXL (VQAScore)

AI-ModelScope/clip-flant5-xxl 是 ModelScope 魔搭社区上的机器学习模型，采用 apache-2.0 许可。

- **Repository**: AI-ModelScope/clip-flant5-xxl
- **License**: apache-2.0
- **Downloads**: 58226
- **Stars**: 1
- **Last updated**: 2024-12-23

Source: https://www.modelscope.cn/models/AI-ModelScope/clip-flant5-xxl

---

# CLIP-FlanT5-XXL (VQAScore)

<!-- Provide a quick summary of what the model is/does. -->

This model is a fine-tuned version of google/flan-t5-xxl designed for image-text retrieval tasks, as presented in the VQAScore paper.

### Model Description

<!-- Provide a longer summary of what this model is. -->

- **Developed by:** Zhiqiu Lin and collaborators
- **Model type:** Vision-Language Generative Model
- **License:** Apache-2.0
- **Finetuned from model:** google/flan-t5-xxl

### Model Sources [optional]

<!-- Provide the basic links for the model. -->

- **Repository:** https://github.com/linzhiqiu/CLIP-FlanT5
- **Paper:** https://arxiv.org/pdf/2404.01291
- **Demo:** https://huggingface.co/spaces/zhiqiulin/VQAScore