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

@@ -0,0 +1,65 @@
+---
+license: other
+license_name: apple-ascl
+license_link: LICENSE
+library_name: mobileclip
+---
+
+# MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training
+
+MobileCLIP was introduced in [MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training
+](https://arxiv.org/pdf/2311.17049.pdf) (CVPR 2024), by Pavan Kumar Anasosalu Vasu, Hadi Pouransari, Fartash Faghri, Raviteja Vemulapalli, Oncel Tuzel.
+
+This repository contains the **MobileCLIP-B (LT)** checkpoint.
+
+![MobileCLIP Performance Figure](fig_accuracy_latency.png)
+
+### Highlights
+
+* Our smallest variant `MobileCLIP-S0` obtains similar zero-shot performance as [OpenAI](https://arxiv.org/abs/2103.00020)'s ViT-B/16 model while being 4.8x faster and 2.8x smaller.
+* `MobileCLIP-S2` obtains better avg zero-shot performance than [SigLIP](https://arxiv.org/abs/2303.15343)'s ViT-B/16 model while being 2.3x faster and 2.1x smaller, and trained with 3x less seen samples.
+* `MobileCLIP-B`(LT) attains zero-shot ImageNet performance of **77.2%** which is significantly better than recent works like [DFN](https://arxiv.org/abs/2309.17425) and [SigLIP](https://arxiv.org/abs/2303.15343) with similar architectures or even [OpenAI's ViT-L/14@336](https://arxiv.org/abs/2103.00020).
+
+## Checkpoints
+
+| Model                                                     | # Seen <BR>Samples (B) | # Params (M) <BR> (img + txt) | Latency (ms) <BR> (img + txt) | IN-1k Zero-Shot <BR> Top-1 Acc. (%) | Avg. Perf. (%) <BR> on 38 datasets |
+|:----------------------------------------------------------|:----------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------------:|:----------------------------------:|
+| [MobileCLIP-S0](https://hf.co/pcuenq/MobileCLIP-S0)       |           13           |          11.4 + 42.4          |           1.5 + 1.6           |                67.8                 |                58.1                |
+| [MobileCLIP-S1](https://hf.co/pcuenq/MobileCLIP-S1)       |           13           |          21.5 + 63.4          |           2.5 + 3.3           |                72.6                 |                61.3                |
+| [MobileCLIP-S2](https://hf.co/pcuenq/MobileCLIP-S2)       |           13           |          35.7 + 63.4          |           3.6 + 3.3           |                74.4                 |                63.7                |
+| [MobileCLIP-B](https://hf.co/pcuenq/MobileCLIP-B)         |           13           |          86.3 + 63.4          |          10.4 + 3.3           |                76.8                 |                65.2                |
+| [MobileCLIP-B (LT)](https://hf.co/pcuenq/MobileCLIP-B-LT) |           36           |          86.3 + 63.4          |          10.4 + 3.3           |                77.2                 |                65.8                |
+
+## How to Use
+
+First, download the desired checkpoint visiting one of the links in the table above, then click the `Files and versions` tab, and download the PyTorch checkpoint.
+For programmatic downloading, if you have `huggingface_hub` installed, you can also run:
+
+```
+huggingface-cli download pcuenq/MobileCLIP-B-LT
+``` 
+
+Then, install [`ml-mobileclip`](https://github.com/apple/ml-mobileclip) by following the instructions in the repo. It uses an API similar to [`open_clip`'s](https://github.com/mlfoundations/open_clip).
+You can run inference with a code snippet like the following:
+
+```py
+import torch
+from PIL import Image
+import mobileclip
+
+model, _, preprocess = mobileclip.create_model_and_transforms('mobileclip_blt', pretrained='/path/to/mobileclip_blt.pt')
+tokenizer = mobileclip.get_tokenizer('mobileclip_blt')
+
+image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)
+text = tokenizer(["a diagram", "a dog", "a cat"])
+
+with torch.no_grad(), torch.cuda.amp.autocast():
+    image_features = model.encode_image(image)
+    text_features = model.encode_text(text)
+    image_features /= image_features.norm(dim=-1, keepdim=True)
+    text_features /= text_features.norm(dim=-1, keepdim=True)
+
+    text_probs = (100.0 * image_features @ text_features.T).softmax(dim=-1)
+
+print("Label probs:", text_probs)
+```

config.json

@@ -0,0 +1,18 @@
+{
+    "embed_dim": 512,
+    "image_cfg": {
+        "image_size": 224,
+        "model_name": "vit_b16"
+    },
+    "text_cfg": {
+        "context_length": 77,
+        "vocab_size": 49408,
+        "dim": 512,
+        "ffn_multiplier_per_layer": 4.0,
+        "n_heads_per_layer": 8,
+        "n_transformer_layers": 12,
+        "norm_layer": "layer_norm_fp32",
+        "causal_masking": true,
+        "model_name": "base"
+    }
+}

mobileclip_blt.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:670844f7a886dd6eff7a9285adfc53f3d3c889c03bfc8354010cb5c6bf27441a
+size 599214572