Hugging Face's logo

sugarquark
/
TMoon

Zero-Shot Object Detection
Safetensors
t5gemma
vision
Model card Files
xet
sugarquark commited on
Commit
b6a6d8c
·
verified ·
1 Parent(s): f6b8428

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -12,7 +12,7 @@ tags:
12
 
13
  - 3D positional embedding (as in the [text encoder replacement](https://huggingface.co/sugarquark/sd15-text-encoder-t5g-2b-ul2-it), [object detection](https://huggingface.co/twodgirl/rotated-position-in-latent-space-fashion-object-detection) and others)
14
  - Supports multiple image aspect ratios
15
- - Vector based prediction model
16
  - AIMv2 vision model
17
  - [T5Gemma](https://huggingface.co/google/t5gemma-2b-2b-ul2-it) text encoder
18
  - [Moondream2](https://huggingface.co/vikhyatk/moondream2/tree/2025-06-21) [dataset](https://huggingface.co/datasets/sugarquark/moonpixs)
 
12
 
13
  - 3D positional embedding (as in the [text encoder replacement](https://huggingface.co/sugarquark/sd15-text-encoder-t5g-2b-ul2-it), [object detection](https://huggingface.co/twodgirl/rotated-position-in-latent-space-fashion-object-detection) and others)
14
  - Supports multiple image aspect ratios
15
+ - Contrastive prediction model
16
  - AIMv2 vision model
17
  - [T5Gemma](https://huggingface.co/google/t5gemma-2b-2b-ul2-it) text encoder
18
  - [Moondream2](https://huggingface.co/vikhyatk/moondream2/tree/2025-06-21) [dataset](https://huggingface.co/datasets/sugarquark/moonpixs)