Downloads · 30 days
11
12% of all-time downloads
siglip2-math-base-patch16-256
dleemiller/siglip2-math-base-patch16-256
siglip2-math-base-patch16-256 is a zero-shot image classification model from dleemiller. Use it for the zero-shot image classification 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 version of siglip2 is fine tuned on shiwk24/MathCanvas-Imagen using the codederivedcaptions split. I trained for 1 epoch on 4M math images, with a random selection between the tikz code or caption using a batch s…
All-time downloads
90
Public
Parameters
375M
1.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.5 GB · 98%
At a glance
- Task
- Zero-Shot Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- siglip
- Access
- Public
- Created
- Nov 7, 2025
- Updated
- Nov 7, 2025
- SHA
- 6b8eaaad
Base models
Datasets
Model card
From the Hugging Face model README
SigLip2 Math
This version of siglip2 is fine tuned on shiwk24/MathCanvas-Imagen using the code_derived_captions split.
I trained for 1 epoch on 4M math images, with a random selection between the tikz code or caption using a batch size of 640.
This is not a classification model, since the loss function was pairwise contrastive loss. Use for embedding or downstream classifier training is recommended.
- Task
- Zero-Shot Image Classification
- Library
- transformers
- Type
- siglip
- License
- apache-2.0
- Created
- Nov 7, 2025
- Updated
- Nov 7, 2025