Downloads · 30 days
4
12% of all-time downloads
vapr_llava_v1_5_13b
VaPR-UCLA/vapr_llava_v1_5_13b
vapr_llava_v1_5_13b is a machine learning model from VaPR-UCLA. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This model is an artifact of the work VaPR – Vision-language Preference alignment for Reasoning (accepted at COLM 2025). 📂 Project Website
All-time downloads
34
Public
Parameters
13B
52.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors52.2 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- llava_llama
- Access
- Public
- Created
- Sep 2, 2025
- Updated
- Oct 3, 2025
- SHA
- af573c7b
Model card
From the Hugging Face model README
VaPR-LLaVA-v1.5-13B
This model is an artifact of the work VaPR – Vision-language Preference alignment for Reasoning (accepted at COLM 2025). 📂 Project Website
Base Model
- Base Model: LLaVA v1.5 13B Instruct
Training Data
This model has been fine-tuned on the VaPR-30k subset dataset available at: VaPR-30k
Citation
If you use this model, please cite the following paper:
inproceedings{
wadhawan2025vapr,
title={Va{PR} - Vision-language Preference alignment for Reasoning},
author={Rohan Wadhawan and Fabrice Y Harel-Canada and Zi-Yi Dou and Suhaila Shakiah and Robinson Piramuthu and Nanyun Peng},
booktitle={Second Conference on Language Modeling},
year={2025},
url={https://openreview.net/forum?id=uBAubFwymy}
}
- Type
- llava_llama
- License
- apache-2.0
- Created
- Sep 2, 2025
- Updated
- Oct 3, 2025