metadata
library_name: transformers
license: cc-by-nc-sa-4.0
tags: []
Model Details
- Model: ReasonCLIP-B32-S0-Rea
- Base model: openai/clip-vit-base-patch32
- Architecture: CLIP ViT-B/32
- Image resolution: 224
- Training stage: Stage 0 - Reasoning
- Training data: Only reasoning caption-image pairs from ReasonLite-42M and ReasonPro-16M
Method
Resources
- GitHub: RISys-Lab/ReasonCLIP
- Paper: arXiv:2606.26794
- Playground: ReasonCLIP Playground
Usage
from transformers import CLIPModel, CLIPProcessor
model_id = "RISys-Lab/ReasonCLIP-B32-S0-Rea"
model = CLIPModel.from_pretrained(model_id)
processor = CLIPProcessor.from_pretrained(model_id)
For the full checkpoint list, see the ReasonCLIP model card.