LibreSAM2tiny

SAM-2.1 Hiera Tiny rehosted for LibreYOLO's LibreSAM promptable segmentation tier.

Source

Derived from facebook/sam2.1-hiera-tiny at commit de431c4043854a71d8101e17995dfe596bf101a5 and the Apache-2.0 facebookresearch/sam2 source release.

Modifications

Learned parameters are unchanged. The upstream Transformers-compatible snapshot files are mirrored here for LibreYOLO distribution. This repository adds LibreYOLO model-card packaging plus LICENSE and NOTICE files for Apache-2.0 redistribution.

Usage

from libreyolo import LibreSAM

model = LibreSAM("sam2-tiny")
result = model("image.jpg", points=[500, 375], labels=[1])

License

Apache License 2.0. See LICENSE and NOTICE.

Downloads last month: 22

Safetensors

Model size

39M params

Tensor type

F32

Inference Providers NEW

Mask Generation

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for LibreYOLO/LibreSAM2tiny

Base model

facebook/sam2.1-hiera-tiny

Finetuned

(8)

this model

Collection including LibreYOLO/LibreSAM2tiny

LibreSAM Promptable Segmentation

Collection

Promptable segmentation (LibreSAM tier): point and box prompts, encode once and prompt many. Image inference; video is out of scope in v1. • 8 items • Updated 2 days ago