Downloads · 30 days
11
42% of all-time downloads
CAT
mahwizzzz/CAT
CAT is a image-text-to-text model from mahwizzzz. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product.
CAT is a minimal and lightweight Vision-Language Model (VLM) designed for efficient training and experimentation. Built using pure PyTorch, the entire model architecture and training logic fits within ~750 lines of co…
All-time downloads
26
Public
Parameters
405M
2.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.6 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Access
- Public
- Created
- Jun 7, 2025
- Updated
- Jun 24, 2025
- SHA
- 8a46aa22
Try a prompt
Model card
From the Hugging Face model README
CAT is a minimal and lightweight Vision-Language Model (VLM) designed for efficient training and experimentation. Built using pure PyTorch, the entire model architecture and training logic fits within ~750 lines of code. It combines a ViT-based image encoder (SigLIP-B/16-224-85M) with a lightweight causal language model (SmolLM2-135M), resulting in a compact 222M parameter model.
Usage:
Follow the install instructions and run the following code:
from models.vision_language_model import CAT
model = CAT.from_pretrained("mahwizzzz/CAT")
- Task
- Image-Text-to-Text
- Created
- Jun 7, 2025
- Updated
- Jun 24, 2025