Upload folder using huggingface_hub

LICENSE

@@ -0,0 +1,46 @@
+Copyright (C) 2024 Apple Inc. All Rights Reserved.
+
+IMPORTANT:  This Apple software is supplied to you by Apple
+Inc. ("Apple") in consideration of your agreement to the following
+terms, and your use, installation, modification or redistribution of
+this Apple software constitutes acceptance of these terms.  If you do
+not agree with these terms, please do not use, install, modify or
+redistribute this Apple software.
+
+In consideration of your agreement to abide by the following terms, and
+subject to these terms, Apple grants you a personal, non-exclusive
+license, under Apple's copyrights in this original Apple software (the
+"Apple Software"), to use, reproduce, modify and redistribute the Apple
+Software, with or without modifications, in source and/or binary forms;
+provided that if you redistribute the Apple Software in its entirety and
+without modifications, you must retain this notice and the following
+text and disclaimers in all such redistributions of the Apple Software.
+Neither the name, trademarks, service marks or logos of Apple Inc. may
+be used to endorse or promote products derived from the Apple Software
+without specific prior written permission from Apple.  Except as
+expressly stated in this notice, no other rights or licenses, express or
+implied, are granted by Apple herein, including but not limited to any
+patent rights that may be infringed by your derivative works or by other
+works in which the Apple Software may be incorporated.
+
+The Apple Software is provided by Apple on an "AS IS" basis.  APPLE
+MAKES NO WARRANTIES, EXPRESS OR IMPLIED, INCLUDING WITHOUT LIMITATION
+THE IMPLIED WARRANTIES OF NON-INFRINGEMENT, MERCHANTABILITY AND FITNESS
+FOR A PARTICULAR PURPOSE, REGARDING THE APPLE SOFTWARE OR ITS USE AND
+OPERATION ALONE OR IN COMBINATION WITH YOUR PRODUCTS.
+
+IN NO EVENT SHALL APPLE BE LIABLE FOR ANY SPECIAL, INDIRECT, INCIDENTAL
+OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) ARISING IN ANY WAY OUT OF THE USE, REPRODUCTION,
+MODIFICATION AND/OR DISTRIBUTION OF THE APPLE SOFTWARE, HOWEVER CAUSED
+AND WHETHER UNDER THEORY OF CONTRACT, TORT (INCLUDING NEGLIGENCE),
+STRICT LIABILITY OR OTHERWISE, EVEN IF APPLE HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+
+-------------------------------------------------------------------------------
+SOFTWARE DISTRIBUTED WITH ML-MobileCLIP:
+
+The ML-MobileCLIP software includes a number of subcomponents with separate
+copyright notices and license terms - please see the file ACKNOWLEDGEMENTS.
+-------------------------------------------------------------------------------

README.md

@@ -1,3 +1,66 @@
----
-license: apple-ascl
----
+---
+library_name: transformers.js
+pipeline_tag: zero-shot-image-classification
+license: other
+tags:
+- mobileclip
+- image-feature-extraction
+- feature-extraction
+---
+
+https://github.com/apple/ml-mobileclip with ONNX weights to be compatible with Transformers.js.
+
+## Usage (Transformers.js)
+
+If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@xenova/transformers) using:
+```bash
+npm i @xenova/transformers
+```
+
+**Example:** Perform zero-shot image classification.
+```js
+import {
+  AutoTokenizer,
+  CLIPTextModelWithProjection,
+  AutoProcessor,
+  CLIPVisionModelWithProjection,
+  RawImage,
+  dot,
+  softmax,
+} from '@xenova/transformers';
+
+const model_id = 'Xenova/mobileclip_s0';
+
+// Load tokenizer and text model
+const tokenizer = await AutoTokenizer.from_pretrained(model_id);
+const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);
+
+// Load processor and vision model
+const processor = await AutoProcessor.from_pretrained(model_id);
+const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id, {
+  quantized: false, // NOTE: vision model is sensitive to quantization.
+});
+
+// Run tokenization
+const texts = ['cats', 'dogs', 'birds'];
+const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });
+
+// Compute text embeddings
+const { text_embeds } = await text_model(text_inputs);
+const normalized_text_embeds = text_embeds.normalize().tolist();
+
+// Read image and run processor
+const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/cats.jpg';
+const image = await RawImage.read(url);
+const image_inputs = await processor(image);
+
+// Compute vision embeddings
+const { image_embeds } = await vision_model(image_inputs);
+const normalized_image_embeds = image_embeds.normalize().tolist();
+
+// Compute probabilities
+const probabilities = normalized_image_embeds.map(
+  x => softmax(normalized_text_embeds.map(y => 100 * dot(x, y)))
+);
+console.log(probabilities); // [[ 0.9989384093386391, 0.001060433633052551, 0.000001157028308360134 ]]
+```

config.json

@@ -0,0 +1,3 @@
+{
+  "model_type": "clip"
+}

onnx/text_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6e9bd5742bfc515889e901634d8a2ff2a57fab8564e4ad3760e800b1a51b77c
+size 169807789

onnx/text_model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9464281b0da079bb7e0bd65b769a96dadca7a076b93ede7faf8e14c621b2d39a
+size 125655548

onnx/text_model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f74b7b3abd9f3a70dcc60115f627bbadb9534606ac841400f9841f49bf980cc
+size 84971030

onnx/text_model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc8d87978623385c17a46331ffb9cb5ab7fe8b61c513c094602b85f08edd0a0b
+size 42799230

onnx/text_model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6758a2bc069c64dce6b8d35a53c828189cfb34e991f1c9426ce2ecb4fb1d5a4
+size 126458232

onnx/text_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8557b10e5c23a0126c6d2e6eba48d240484979007917d128953b31618a04211
+size 42799238

onnx/text_model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8557b10e5c23a0126c6d2e6eba48d240484979007917d128953b31618a04211
+size 42799238

onnx/vision_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17d3c037b1d488c10c50e09f6009ea5a198caef4e0e8f4ea5617b7cb2d067ac0
+size 45543630

onnx/vision_model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f30b8b45dd0b9fb0df7239b8836bcb2d49ab4a3f2d47b912b9311de0c63bda54
+size 36533217

onnx/vision_model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22b1d36ecc6837e8205aee05003440a25e1c1ee0c7e2945dbb9dd597211c59dc
+size 22876479

onnx/vision_model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a1b45f57fb9f3cde9d325759883e9451d7281336caeb9c576ae918e72080f0b
+size 11846808

onnx/vision_model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d122be38f8bef9cb165c63f67af2da5ddf037dc3239b9785b83f4ad4a683d6ea
+size 36697020

onnx/vision_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcbd153d1aa1314fb72ea39b20c37e0572e7e7b05359b51f3efee5d682658472
+size 11846843

onnx/vision_model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcbd153d1aa1314fb72ea39b20c37e0572e7e7b05359b51f3efee5d682658472
+size 11846843

preprocessor_config.json

@@ -0,0 +1,18 @@
+{
+  "crop_size": {
+    "height": 256,
+    "width": 256
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": false,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_processor_type": "CLIPFeatureExtractor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 256
+  }
+}

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "!",
+  "processor_class": "CLIPProcessor",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}