Downloads · 30 days
17
2% of all-time downloads
TIGER-Lab/ABC-Qwen2VL-Pretrain
ABC-Qwen2VL-Pretrain is a image-text-to-text model from TIGER-Lab. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for peft.
Pretrained adapter for ABC: Acheiving Better Control of Multiomodal Embeddings using VLMs.
Downloads · 30 days
17
2% of all-time downloads
All-time downloads
1.1K
Public
Repo size
466 MB
Likes
1
Public
Click a slice to open those files.
.safetensors466 MB · 99%
From the Hugging Face model README
Pretrained adapter for ABC: Acheiving Better Control of Multiomodal Embeddings using VLMs.
This model is trained on top of Qwen2VL-Instruct.
For more information, please refer to Website.
Code: https://github.com/TIGER-AI-Lab/ABC
@misc{schneider2025abcachievingbettercontrol,
title={ABC: Achieving Better Control of Multimodal Embeddings using VLMs},
author={Benjamin Schneider and Florian Kerschbaum and Wenhu Chen},
year={2025},
eprint={2503.00329},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2503.00329},
}