| license: apache-2.0 | |
| library_name: libreyolo | |
| tags: | |
| - mask-generation | |
| - image-segmentation | |
| - sam | |
| # LibreSAMlarge | |
| Segment Anything (SAM-1) ViT-Large, mirrored for LibreYOLO. | |
| ## Source | |
| Mirrored from [facebook/sam-vit-large](https://huggingface.co/facebook/sam-vit-large). | |
| Copyright (c) Meta Platforms, Inc. and affiliates. | |
| Licensed under the Apache License, Version 2.0. | |
| ## Modifications | |
| None. The weights and configuration are Meta's, byte for byte. This repository | |
| exists so LibreYOLO can serve them from its own organisation rather than | |
| depending on a third-party repository remaining available. | |
| Upstream also publishes `pytorch_model.bin` (a duplicate of the safetensors | |
| weights) and `tf_model.h5`. Neither is mirrored, because LibreYOLO loads the | |
| safetensors file. | |
| ## Usage | |
| ```python | |
| from libreyolo import LibreYOLO | |
| model = LibreYOLO("LibreSAMlarge.pt") | |
| ``` | |
| ## License | |
| Apache License 2.0. See the [`LICENSE`](./LICENSE) and [`NOTICE`](./NOTICE) | |
| files in this repository. | |