Update README (#1)

- Update README (cf81c326387edbb4ec5866e154a7fa2b36a03510)
- Update README (4e02c778c7bff025c4f17421db8c3c0f81762a5c)


Co-authored-by: Pedro Cuenca <[email protected]>

README.md

@@ -1,10 +1,28 @@
 ---
 license: apache-2.0
 pipeline_tag: mask-generation
-library_name: sam2
+library_name: coreml
 ---
 
-### Citation
+# SAM2 Tiny Core ML
+
+SAM 2 (Segment Anything in Images and Videos), is a collection of foundation models from FAIR that aim to solve promptable visual segmentation in images and videos. See the [SAM 2 paper](https://arxiv.org/abs/2408.00714) for more information.
+
+This is the Core ML version of [SAM 2 Tiny](https://huggingface.co/facebook/sam2-hiera-tiny), and is suitable for use with the [SAM2 Studio demo app](https://github.com/huggingface/sam2-swiftui). It was converted in `float16` precision using [this fork](https://github.com/FL33TW00D/segment-anything-2/tree/feature/SAM2) of the original code repository.
+
+## Download
+
+Install `huggingface-cli`
+
+```bash
+brew install huggingface-cli
+```
+
+```bash
+huggingface-cli download --local-dir models coreml-projects/coreml-sam2-tiny
+```
+
+## Citation
 
 To cite the paper, model, or software, please use the below:
 ```
@@ -15,4 +33,4 @@ To cite the paper, model, or software, please use the below:
   url={https://arxiv.org/abs/2408.00714},
   year={2024}
 }
-```
+```