Downloads · 30 days
24
19% of all-time downloads
SPY_Qwen2-VL-7B-Instruct_NCA-P
achernarwang/SPY_Qwen2-VL-7B-Instruct_NCA-P
SPY_Qwen2-VL-7B-Instruct_NCA-P is a image-text-to-text model from achernarwang. 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 transformers. The card lists the license as apache-2.0.
This model is a fine-tuned version of Qwen2-VL-7B, trained on our SPY-Tune dataset using the proposed NCA-P alignment algorithm (which is a variant of NCA).
All-time downloads
124
Public
Parameters
8.3B
16.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.6 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen2_vl
- Access
- Public
- Created
- Oct 20, 2025
- Updated
- Oct 21, 2025
- SHA
- 473bb456
Try a prompt
Base models
Model card
From the Hugging Face model README
SPY_Qwen2-VL-7B-Instruct_NCA-P
This model is a fine-tuned version of Qwen2-VL-7B, trained on our SPY-Tune dataset using the proposed NCA-P alignment algorithm (which is a variant of NCA).
It serves as the official checkpoint used in our ACM Multimedia 2025 BNI Oral paper:
Specify Privacy Yourself: Assessing Inference-Time Personalized Privacy Preservation Ability of Large Vision-Language Models
The model aims to enhance personalized privacy-preserving abilities of large vision-language models during inference time, enabling controllable trade-offs between utility and privacy according to user-specified privacy intents.
For more details about the dataset, training process, and evaluation metrics, please refer to our GitHub repository: https://github.com/achernarwang/specify-privacy-yourself
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- qwen2_vl
- License
- apache-2.0
- Created
- Oct 20, 2025
- Updated
- Oct 21, 2025