Add attribution README — credit: OpenAI

README.md

@@ -0,0 +1,56 @@
+---
+license: mit
+tags:
+- mirror
+- xai
+- multimodal
+- clip
+- zero-shot-image-classification
+---
+
+# CLIP ViT-B/32 (OpenAI) — xaitalk mirror
+
+This is a **bit-identical mirror** of the canonical artifact from OpenAI.
+
+The mirror exists only as a resilience fallback for the
+[xaitalk](https://github.com/xaitalk/xaitalk) library — the upstream remains
+authoritative. All credit and licensing for the model belong to the original
+authors.
+
+## Attribution
+
+| Field | Value |
+|---|---|
+| **Original authors** | OpenAI |
+| **Upstream (authoritative)** | https://huggingface.co/openai/clip-vit-base-patch32 |
+| **Source repo** | https://github.com/openai/CLIP |
+| **Paper** | https://arxiv.org/abs/2103.00020 (Radford et al. 2021) |
+| **License** | `mit` (inherited from upstream — please respect upstream's terms) |
+| **Mirror file** | `pytorch_model.bin` |
+| **SHA-256** | `a63082132ba4f97a80bea76823f544493bffa8082296d62d71581a4feff1576f` |
+| **Size** | 605,247,071 bytes (577.2 MB) |
+
+## How xaitalk loads this file
+
+```python
+from xaitalk.hub import ensure_model
+weights_path = ensure_model("clip-vit-b32")
+# Tries the canonical upstream first; falls back to this xaitalk mirror
+# automatically if upstream is unreachable.
+```
+
+## Why mirror?
+
+xaitalk's research-grade reproducibility claim relies on every weight file
+being recoverable years from now. We mirror artifacts ≤ 2.5 GB under
+`xaitalk/*-mirror` so the pipeline survives upstream URL changes, repo
+renames, or deletions. Bit-level parity with the canonical is asserted in
+CI via `python -m xaitalk.hub verify-mirrors`.
+
+## Citation
+
+If you use this model, **please cite the original paper** (not the mirror):
+
+```
+https://arxiv.org/abs/2103.00020 (Radford et al. 2021)
+```