Update README with hycoclip-vit-s

README.md

@@ -0,0 +1,99 @@
+---
+library_name: onnx
+pipeline_tag: feature-extraction
+license: cc-by-nc-4.0
+tags:
+  - onnx
+  - vision
+  - clip
+  - hyperbolic
+  - image-embedding
+  - hyperboloid
+  - non-euclidean
+  - lorentz
+  - meru
+  - hycoclip
+language:
+  - en
+---
+
+# Hyperbolic CLIP Models (ONNX)
+
+This repository contains **ONNX exports** of hyperbolic vision-language models for **hyperbolic image embeddings**.
+
+## Available Models
+
+| Model | Architecture | Embedding Dim | Size | Path |
+|-------|--------------|---------------|------|------|
+| **hycoclip-vit-s** | ViT-S/16 | 513 | ~84 MB | `hycoclip-vit-s/model.onnx` |
+
+## Quick Start
+
+```python
+import onnxruntime as ort
+import numpy as np
+from huggingface_hub import hf_hub_download
+
+# Download a model
+onnx_path = hf_hub_download(
+    repo_id="mnm-matin/hyperbolic-clip",
+    filename="hycoclip-vit-s/model.onnx"  # or other model path
+)
+
+# Load and run
+session = ort.InferenceSession(onnx_path)
+image = np.random.rand(1, 3, 224, 224).astype(np.float32)  # Your preprocessed image
+embedding, curvature = session.run(None, {"image": image})
+
+print(f"Embedding shape: {embedding.shape}")  # (1, 513) - hyperboloid format
+```
+
+## Model Details
+
+All models output embeddings in **Lorentz/Hyperboloid format**:
+- Output: `(t, x₁...xₙ)` where `t = √(1/c + ‖x‖²)`
+- Embedding dim: 513 (1 time component + 512 spatial)
+- Curvature `c` is learned and exported as secondary output
+
+### Converting to Poincaré Ball
+
+```python
+t = embedding[:, 0:1]   # time component
+x = embedding[:, 1:]    # spatial components
+poincare = x / (t + 1)  # stereographic projection
+```
+
+## Usage with HyperView
+
+```python
+import hyperview as hv
+from huggingface_hub import hf_hub_download
+
+# Download model
+model_path = hf_hub_download("mnm-matin/hyperbolic-clip", "hycoclip-vit-s/model.onnx")
+
+# Use with HyperView
+ds = hv.Dataset("my_images")
+ds.add_images_dir("/path/to/images")
+ds.compute_embeddings(onnx_path=model_path)
+hv.show(ds)
+```
+
+## License
+
+**CC-BY-NC-4.0** (Non-commercial use only)
+
+Based on:
+- [PalAvik/hycoclip](https://github.com/PalAvik/hycoclip)
+- [facebookresearch/meru](https://github.com/facebookresearch/meru)
+
+## Citation
+
+```bibtex
+@inproceedings{desai2023hyperbolic,
+  title={Hyperbolic Image-Text Representations},
+  author={Desai, Karan and Nickel, Maximilian and Rajpurohit, Tanmay and Johnson, Justin and Vedantam, Ramakrishna},
+  booktitle={ICML},
+  year={2023}
+}
+```