Downloads · 30 days
9
10% of all-time downloads
QA-CLIP-ViT-B-16-SAFETENSORS
exdysa/QA-CLIP-ViT-B-16-SAFETENSORS
QA-CLIP-ViT-B-16-SAFETENSORS is a zero-shot image classification model from exdysa. Use it for the zero-shot image classification 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.
[!IMPORTANT] Original Model Link : https://huggingface.co/TencentARC/QA-CLIP-ViT-B-16-SAFETENSORS
All-time downloads
91
Public
Parameters
188M
1.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors753 MB · 100%
Parameter types
How the weights are stored.
F32188M · 100%
Base models
Model card
From the Hugging Face model README
[!IMPORTANT] Original Model Link : https://huggingface.co/TencentARC/QA-CLIP-ViT-B-16-SAFETENSORS
name: QA-CLIP-ViT-B-16-SAFETENSORS
base_model: openai/clip-vit-base-patch16
license: apache-2.0
pipeline_tag: zero-shot-image-classification
tasks: zero-shot-image-classification
language: zh
QA-CLIP-ViT-B-16-SAFETENSORS
QA-CLIP-ViT-B-16 https://github.com/TencentARC-QQ/QA-CLIP
- Task
- Zero-Shot Image Classification
- Type
- chinese_clip
- License
- apache-2.0
- Languages
- zh
- Created
- Dec 1, 2025
- Updated
- Dec 1, 2025