Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model/clip-vit-base-patch32_float16_static.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,57 @@
+---
+license: mit
+tags:
+  - coreai
+  - clip
+  - apple-silicon
+  - on-device
+---
+
+# CLIP ViT-B/32 — Core AI export (official recipe)
+
+fp16 static export of [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32)
+via apple/coreai-models' official recipe (`models/clip/export.py`), with one change: text
+inputs are padded to the full 77-token context (`padding="max_length"`) so free-text
+queries work, instead of the recipe's 7-token example trace.
+
+Runs out of the box with [CoreAIKit](https://github.com/john-rocky/coreai-kit)'s
+`ImageTextEncoder`:
+
+```swift
+let encoder = try await ImageTextEncoder()   // downloads this repo
+let imageVec = try await encoder.encode(image: cgImage)
+let textVec  = try await encoder.encode(text: "red bike at the beach")
+let score = ImageTextEncoder.cosineSimilarity(imageVec, textVec)
+```
+
+## Bundle layout
+
+```
+model/
+├── clip-vit-base-patch32_float16_static.aimodel
+└── tokenizer.json
+```
+
+## Graph contract
+
+| | name | shape | dtype |
+|---|---|---|---|
+| input | `pixel_values` | [1, 3, 224, 224] | fp16 |
+| input | `input_ids` | [3, 77] | int32 |
+| input | `attention_mask` | [3, 77] | int32 |
+| output | `image_embeds` | [1, 512] | fp16, L2-normalized |
+| output | `text_embeds` | [3, 512] | fp16, L2-normalized |
+| output | `logits_per_image` / `logits_per_text` | [1, 3] / [3, 1] | fp16 |
+
+Preprocessing: 224×224 resize + CLIP mean/std normalization (handled by
+`ImageTextEncoder`).
+
+## Performance
+
+M4 Max: ~3.7 ms per image on the Neural Engine (fp16). Requires macOS 27 beta /
+iOS 27 beta (device — the CoreAI framework is not in the iOS Simulator SDK).
+
+## License
+
+Model weights: MIT (OpenAI CLIP); see the upstream repo. Export recipe:
+BSD-3-Clause (apple/coreai-models).

model/clip-vit-base-patch32_float16_static.aimodel/main.hash

@@ -0,0 +1 @@
+�	M����X$'r$�ĬK̖�����_�2��>h

model/clip-vit-base-patch32_float16_static.aimodel/main.mlirb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4094dfea3cfc7582427721e24eac4ac4bcc9619b983fafdad5ff432a0933e68
+size 302771548

model/clip-vit-base-patch32_float16_static.aimodel/metadata.json

@@ -0,0 +1,7 @@
+{
+  "license" : "MIT",
+  "author" : "A. Radford et al.",
+  "creationDate" : "20260611T225847Z",
+  "description" : "CLIP (Contrastive Language-Image Pretraining) learns joint representations of images and text, enabling zero-shot image classification with natural language labels. Source: https:\/\/huggingface.co\/openai\/clip-vit-base-patch32",
+  "assetVersion" : "2.0"
+}