Downloads · 30 days
0
kevinqz/LingBot-Vision-ViT-Large-CoreAI
LingBot-Vision-ViT-Large-CoreAI is a image feature extraction model from kevinqz. Use it for the image feature extraction task on the model card, and read the license before you ship it in a product. It is set up for coreai. The card lists the license as apache-2.0.
Canonical: kevinqz/LingBot-Vision-ViT-Large-CoreAI — source of truth.
Downloads · 30 days
0
Access
Public
Updated Jul 7, 2026
Repo size
1.2 GB
Likes
0
Public
Click a slice to open those files.
.mlirb1.2 GB · 100%
From the Hugging Face model README
Canonical:
kevinqz/LingBot-Vision-ViT-Large-CoreAI— source of truth.
An Apple Core AI conversion of robbyant/lingbot-vision-vit-large — a vision encoder (ViT backbone) that maps an image to normalized per-patch feature tokens, for dense downstream tasks (depth, segmentation, spatial perception). Produced by coreai-fabric and indexed by coreai-catalog.
Feature backbone, not an end task. This is a frozen encoder: it emits per-patch feature tokens, not depths / masks / labels. The host owns image preprocessing (resize to the static size, ImageNet mean/std) and any downstream head. Use the upstream repo for the preprocessing + task heads.
| Field | Value |
|---|---|
| Parameters | 0.3B |
| Architecture | transformer |
| Capabilities | image-feature-extraction |
| Image size | 512px (static) |
| Patch size | 16 |
| Embed dim | 1024 |
| Patch tokens | 1024 |
| Quantization / precision | none / float32 |
| On-disk size | 1.1 GB |
| Asset kind | single-graph ViT encoder (image -> per-patch tokens) |
| assetVersion | 2.0 |
The bundle is a single static-size graph: image [1,3,S,S] in → normalized
patch_tokens [1, (S/16)^2, embed_dim] out. You supply the image
preprocessing (resize to S, ImageNet normalize) and any downstream head in your
host code (Swift or Python).
pip install coreai-catalog && coreai-catalog install lingbot-vision-vit-large
minimum_os v27,
so the on-device Swift runtime requires macOS/iOS 27+. A Mac on macOS 26 can
convert and inspect it but not run it on-device.coreai-fabric verify.| Field | Value |
|---|---|
| Base model | robbyant/lingbot-vision-vit-large @ 5e0370623d4fa5db945d00bc47a8545eed407d6b |
| Converted by | models/lingbot/export.py (version not reported) |
| Recipe | lingbot-vision-vit-large (recipe_source: fabric) |
| Precision / quantization | float32 / none |
| Conversion date | 2026-07-07 |
Machine-readable, in this repo:
parity-report.json ·
reproduce-manifest.json · LICENSE.
Weights licensed apache-2.0 — see the bundled LICENSE. This artifact is a converted derivative of the base backbone: its
weights were converted to Apple Core AI format. The conversion itself is
community work.
lingbot-vision-vit-large.aimodel pipeline that produced this asset.Community conversion. Not produced, hosted, or endorsed by Apple. Apple and Core AI are trademarks of Apple Inc., used here only to describe the target runtime/format.