ModelListedExternal

TMoon

3D positional embedding (as in the text encoder replacement, object detection and others) Supports multiple image aspect ratios Contrastive prediction model AIMv2 vision model T5Gemma text encoder Moondream2 dataset

Sourcehuggingface.co/sugarquark/TMoon/tree/cc43f903922cc2a25d04cd6cb289ff9d9717769c

KindOtherBase modelapple/aimv2-large-patch14-448VersionModelCgrade

Model source

Kind: Other
File size: 93.4 MB
Base model: apple/aimv2-large-patch14-448
Version: vModel
Updated: Oct 10, 2026
Source: Hugging Face

Source description

TMoon

3D positional embedding (as in the text encoder replacement, object detection and others)
Supports multiple image aspect ratios
Contrastive prediction model
AIMv2 vision model
T5Gemma text encoder
Moondream2 dataset

Sources

1 source

Hugging FacePrimaryVersion cc43f903922cc2a25d04cd6cb289ff9d9717769c

huggingface.co/sugarquark/TMoon/tree/cc43f903922cc2a25d04cd6cb289ff9d9717769c

Verified Oct 10

Model artifacts

1 artifact

model.safetensors

safetensors · 93.4 MB · SHA-256 c97a94fe6013…a2a4 · Hugging Face

Download file

Source excerpts

2 excerpts

ReadmeAug 1huggingface.co/sugarquark/TMoon

--- license: apache-2.0 base_model: - apple/aimv2-large-patch14-448 pipeline_tag: zero-shot-object-detection tags: - t5gemma - vision --- # TMoon - 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) - Supports multiple image aspect ratios - Contrastive prediction model - AIMv2 vision model - [T5Gemma](https://huggingface.co/google/t5gemma-2b-2b-ul2-it) text encoder - [Moondream2](https://huggingface.co/vikhyatk/moondream2/tree/2025-06-21) [dataset](https://huggingface.co/datasets/sugarquark/moonpixs) ![](images/horizon.jpg)

NoteAug 1huggingface.co/sugarquark/TMoon

Source context: 0 downloads · 0 likes · Pipeline zero-shot-object-detection · Repo sugarquark/TMoon