Add model card

README.md

@@ -0,0 +1,37 @@
+---
+license: mit
+tags:
+  - onnx
+  - video-classification
+  - clip
+base_model: microsoft/xclip-base-patch16-kinetics-600
+---
+
+# xclip-onnx
+
+Two ONNX graphs exported from
+[microsoft/xclip-base-patch16-kinetics-600](https://huggingface.co/microsoft/xclip-base-patch16-kinetics-600)
+(MIT license, code and weights) at revision
+`e4921c41fc296102aae210d43d4127c5e3e51928`, for use through `wasi:nn`
+where no PyTorch runtime is available. Used by
+[`ffrwd/describe`](https://github.com/imbcmdth/ffrwd-package-describe).
+
+There is no official or community ONNX export of X-CLIP; these are
+produced by `scripts/export_xclip.py` in that repository, opset 17, no
+dynamic axes, and validated against the PyTorch model on export (max
+absolute diff ~1e-6, float32 rounding noise).
+
+## Files
+
+| file | tower | input | output |
+| --- | --- | --- | --- |
+| `video_tower.onnx` | `get_video_features` | `pixel_values` `[1, 8, 3, 224, 224]` fp32 | `video_embeds` `[1, 512]` |
+| `text_tower.onnx` | `get_text_features` | `input_ids`, `attention_mask`, both `[1, 77]` i64 | `text_embeds` `[1, 512]` |
+
+Both towers' output is the model's `pooler_output` field, which
+X-CLIP overwrites with the projected embedding (not the tower's own
+pooled hidden state) - the field the export script pulls explicitly.
+
+## License
+
+MIT, following the source model.