Add files using upload-large-folder tool

.gitattributes

@@ -32,3 +32,4 @@ clip/google/siglip-base-patch16-256/model.safetensors filter=lfs diff=lfs merge=
 clip/laion/CLIP-ViT-B-32-laion2B-s34B-b79K/open_clip_model.safetensors filter=lfs diff=lfs merge=lfs -text
 clip/laion/CLIP-ViT-B-32-laion2B-s34B-b79K/model.safetensors filter=lfs diff=lfs merge=lfs -text
 clip/facebook/metaclip-g14-fullcc2.5b/model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
+clip/laion/CLIP-ViT-L-14-laion2B-s32B-b82K/open_clip_pytorch_model.safetensors filter=lfs diff=lfs merge=lfs -text

clip/apple/DFN5B-CLIP-ViT-H-14/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

clip/apple/DFN5B-CLIP-ViT-H-14/LICENSE

@@ -0,0 +1,88 @@
+Disclaimer: IMPORTANT: This Apple Machine Learning Research Model is
+specifically developed and released by Apple Inc. ("Apple") for the sole purpose
+of scientific research of artificial intelligence and machine-learning
+technology. “Apple Machine Learning Research Model” means the model, including
+but not limited to algorithms, formulas, trained model weights, parameters,
+configurations, checkpoints, and any related materials (including
+documentation).
+
+This Apple Machine Learning Research Model is provided to You by
+Apple in consideration of your agreement to the following terms, and your use,
+modification, creation of Model Derivatives, and or redistribution of the Apple
+Machine Learning Research Model constitutes acceptance of this Agreement. If You
+do not agree with these terms, please do not use, modify, create Model
+Derivatives of, or distribute this Apple Machine Learning Research Model or
+Model Derivatives.
+
+* License Scope: In consideration of your agreement to abide by the following
+  terms, and subject to these terms, Apple hereby grants you a personal,
+  non-exclusive, worldwide, non-transferable, royalty-free, revocable, and
+  limited license, to use, copy, modify, distribute, and create Model
+  Derivatives (defined below) of the Apple Machine Learning Research Model
+  exclusively for Research Purposes. You agree that any Model Derivatives You
+  may create or that may be created for You will be limited to Research Purposes
+  as well. “Research Purposes” means non-commercial scientific research and
+  academic development activities, such as experimentation, analysis, testing
+  conducted by You with the sole intent to advance scientific knowledge and
+  research. “Research Purposes” does not include any commercial exploitation,
+  product development or use in any commercial product or service.
+
+* Distribution of Apple Machine Learning Research Model and Model Derivatives:
+  If you choose to redistribute Apple Machine Learning Research Model or its
+  Model Derivatives, you must provide a copy of this Agreement to such third
+  party, and ensure that the following attribution notice be provided: “Apple
+  Machine Learning Research Model is licensed under the Apple Machine Learning
+  Research Model License Agreement.” Additionally, all Model Derivatives must
+  clearly be identified as such, including disclosure of modifications and
+  changes made to the Apple Machine Learning Research Model. The name,
+  trademarks, service marks or logos of Apple may not be used to endorse or
+  promote Model Derivatives or the relationship between You and Apple. “Model
+  Derivatives” means any models or any other artifacts created by modifications,
+  improvements, adaptations, alterations to the architecture, algorithm or
+  training processes of the Apple Machine Learning Research Model, or by any
+  retraining, fine-tuning of the Apple Machine Learning Research Model.
+
+* No Other License: 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, trademark, and similar intellectual property rights
+  worldwide that may be infringed by the Apple Machine Learning Research Model,
+  the Model Derivatives or by other works in which the Apple Machine Learning
+  Research Model may be incorporated.
+
+* Compliance with Laws: Your use of Apple Machine Learning Research Model must
+  be in compliance with all applicable laws and regulations.
+
+* Term and Termination: The term of this Agreement will begin upon your
+  acceptance of this Agreement or use of the Apple Machine Learning Research
+  Model and will continue until terminated in accordance with the following
+  terms. Apple may terminate this Agreement at any time if You are in breach of
+  any term or condition of this Agreement. Upon termination of this Agreement,
+  You must cease to use all Apple Machine Learning Research Models and Model
+  Derivatives and permanently delete any copy thereof. Sections 3, 6 and 7 will
+  survive termination.
+
+* Disclaimer and Limitation of Liability: This Apple Machine Learning Research
+  Model and any outputs generated by the Apple Machine Learning Research Model
+  are provided 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 MACHINE LEARNING RESEARCH MODEL OR OUTPUTS GENERATED BY
+  THE APPLE MACHINE LEARNING RESEARCH MODEL. You are solely responsible for
+  determining the appropriateness of using or redistributing the Apple Machine
+  Learning Research Model and any outputs of the Apple Machine Learning Research
+  Model and assume any risks associated with Your use of the Apple Machine
+  Learning Research Model and any output and results. IN NO EVENT SHALL APPLE BE
+  LIABLE FOR ANY SPECIAL, INDIRECT, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+  IN ANY WAY OUT OF THE USE, REPRODUCTION, MODIFICATION AND/OR DISTRIBUTION OF
+  THE APPLE MACHINE LEARNING RESEARCH MODEL AND ANY OUTPUTS OF THE APPLE MACHINE
+  LEARNING RESEARCH MODEL, 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.
+
+* Governing Law: This Agreement will be governed by and construed under the laws
+  of the State of California without regard to its choice of law principles. The
+  Convention on Contracts for the International Sale of Goods shall not apply to
+  the Agreement except that the arbitration clause and any arbitration hereunder
+  shall be governed by the Federal Arbitration Act, Chapters 1 and 2. 
+
+Copyright (C) 2025 Apple Inc. All Rights Reserved.

clip/apple/DFN5B-CLIP-ViT-H-14/README.md

@@ -0,0 +1,107 @@
+---
+license: apple-amlr
+license_name: apple-sample-code-license
+license_link: LICENSE
+---
+A CLIP (Contrastive Language-Image Pre-training) model trained on DFN-5B. 
+Data Filtering Networks (DFNs) are small networks used to automatically filter large pools of uncurated data. 
+This model was trained on 5B images that were filtered from a pool of 43B uncurated image-text pairs 
+(12.8B image-text pairs from CommonPool-12.8B + 30B additional public image-text pairs).
+
+This model has been converted to PyTorch from the original JAX checkpoints from Axlearn (https://github.com/apple/axlearn). 
+These weights are directly usable in OpenCLIP (image + text).
+
+
+## Model Details
+
+- **Model Type:**  Contrastive Image-Text, Zero-Shot Image Classification.
+- **Dataset:** DFN-5b
+- **Papers:**
+  - Data Filtering Networks: https://arxiv.org/abs/2309.17425
+- **Samples Seen:** 39B  
+## Model Metrics 
+
+| Eval Dataset                |   Metric |
+|:-----------------------|---------:|
+| ImageNet 1k            | 0.8344   |
+| Caltech-101            | 0.954935 |
+| CIFAR-10               | 0.9878   |
+| CIFAR-100              | 0.9051   |
+| CLEVR Counts           | 0.2966   |
+| CLEVR Distance         | 0.2124   |
+| Country211             | 0.343981 |
+| Describable Textures   | 0.706383 |
+| EuroSAT                | 0.654815 |
+| FGVC Aircraft          | 0.714055 |
+| Food-101               | 0.956792 |
+| GTSRB                  | 0.677514 |
+| ImageNet Sketch        | 0.727308 |
+| ImageNet v2            | 0.773    |
+| ImageNet-A             | 0.6988   |
+| ImageNet-O             | 0.381    |
+| ImageNet-R             | 0.929367 |
+| KITTI Vehicle Distance | 0.336146 |
+| MNIST                  | 0.8579   |
+| ObjectNet              | 0.765156 |
+| Oxford Flowers-102     | 0.899534 |
+| Oxford-IIIT Pet        | 0.965515 |
+| Pascal VOC 2007        | 0.818309 |
+| PatchCamelyon          | 0.653625 |
+| Rendered SST2          | 0.546403 |
+| RESISC45               | 0.750476 |
+| Stanford Cars          | 0.957592 |
+| STL-10                 | 0.989    |
+| SUN397                 | 0.769149 |
+| SVHN                   | 0.676168 |
+| Flickr                 | 0.8645   |
+| MSCOCO                 | 0.631112 |
+| WinoGAViL              | 0.556329 |
+| iWildCam               | 0.205549 |
+| Camelyon17             | 0.705034 |
+| FMoW                   | 0.207482 |
+| Dollar Street          | 0.699766 |
+| GeoDE                  | 0.928184 |
+| **Average**                | **0.698347** |
+## Model Usage
+### With OpenCLIP
+```
+import torch
+import torch.nn.functional as F
+from urllib.request import urlopen
+from PIL import Image
+from open_clip import create_model_from_pretrained, get_tokenizer 
+
+model, preprocess = create_model_from_pretrained('hf-hub:apple/DFN5B-CLIP-ViT-H-14')
+tokenizer = get_tokenizer('ViT-H-14')
+
+image = Image.open(urlopen(
+    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
+))
+image = preprocess(image).unsqueeze(0)
+
+labels_list = ["a dog", "a cat", "a donut", "a beignet"]
+text = tokenizer(labels_list, context_length=model.context_length)
+
+with torch.no_grad(), torch.cuda.amp.autocast():
+    image_features = model.encode_image(image)
+    text_features = model.encode_text(text)
+    image_features = F.normalize(image_features, dim=-1)
+    text_features = F.normalize(text_features, dim=-1)
+
+    text_probs = torch.sigmoid(image_features @ text_features.T * model.logit_scale.exp() + model.logit_bias)
+
+zipped_list = list(zip(labels_list, [round(p.item(), 3) for p in text_probs[0]]))
+print("Label probabilities: ", zipped_list)
+```
+
+## Citation
+```bibtex
+@article{fang2023data,
+  title={Data Filtering Networks},
+  author={Fang, Alex and Jose, Albin Madappally and Jain, Amit and Schmidt, Ludwig and Toshev, Alexander and Shankar, Vaishaal},
+  journal={arXiv preprint arXiv:2309.17425},
+  year={2023}
+}
+
+```
+

clip/apple/DFN5B-CLIP-ViT-H-14/config.json

@@ -0,0 +1,165 @@
+{
+  "_commit_hash": null,
+  "architectures": [
+    "CLIPModel"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 1024,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 49407,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 77,
+    "min_length": 0,
+    "model_type": "clip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 49408,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.27.1",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 49409
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 1280,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 5120,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 32,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.27.1",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  }
+}

clip/apple/DFN5B-CLIP-ViT-H-14/open_clip_config.json

@@ -0,0 +1,34 @@
+{
+    "model_cfg": {
+        "embed_dim": 1024,
+        "quick_gelu": true,
+        "vision_cfg": {
+            "image_size": 224,
+            "layers": 32,
+            "width": 1280,
+            "head_width": 80,
+            "patch_size": 14
+        },
+        "text_cfg": {
+            "context_length": 77,
+            "vocab_size": 49408,
+            "width": 1024,
+            "heads": 16,
+            "layers": 24
+        }
+    },
+    "preprocess_cfg": {
+        "mean": [
+            0.48145466,
+            0.4578275,
+            0.40821073
+        ],
+        "std": [
+            0.26862954,
+            0.26130258,
+            0.27577711
+        ],
+        "interpolation": "bicubic",
+        "resize_mode": "squash"
+    }
+}

clip/apple/DFN5B-CLIP-ViT-H-14/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

clip/apple/DFN5B-CLIP-ViT-H-14/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
+  },
+  "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,
+  "name_or_path": "openai/clip-vit-large-patch14",
+  "pad_token": "<|endoftext|>",
+  "special_tokens_map_file": "./special_tokens_map.json",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

clip/facebook/metaclip-l14-400m/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

clip/facebook/metaclip-l14-400m/README.md

@@ -0,0 +1,46 @@
+---
+license: cc-by-nc-4.0
+tags:
+- vision 
+- metaclip
+widget:
+- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/cat-dog-music.png
+  candidate_labels: playing music, playing sports
+  example_title: Cat & Dog
+---
+
+# MetaCLIP model, large-sized version, patch resolution 14
+
+MetaCLIP model applied to 400 million data points of CommonCrawl (CC). It was introduced in the paper [Demystifying CLIP Data](https://arxiv.org/abs/2309.16671) by Xu et al. and first released in [this repository](https://github.com/facebookresearch/MetaCLIP). 
+
+Disclaimer: The team releasing MetaCLIP did not write a model card for this model so this model card has been written by the Hugging Face team.
+
+## Model description
+
+The [Demystifying CLIP Data](https://arxiv.org/abs/2309.16671) paper aims to reveal CLIP’s method around training data curation. OpenAI never open-sourced code regarding their data preparation pipeline.
+
+<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/clip_overview.jpg"
+alt="drawing" width="600"/>
+
+<small> CLIP high-level overview. Taken from the <a href="https://arxiv.org/abs/2103.00020">CLIP paper</a>. </small>
+
+## Intended uses & limitations
+
+You can use the raw model for linking images with text in a shared embedding space. This enables things like zero-shot image classification, text-based image retrieval, image-based text retrieval, etc.
+
+### How to use
+
+We refer to the [docs](https://huggingface.co/docs/transformers/main/en/model_doc/clip#usage). Just replace the names of the models on the hub.
+
+### BibTeX entry and citation info
+
+```bibtex
+@misc{xu2023demystifying,
+      title={Demystifying CLIP Data}, 
+      author={Hu Xu and Saining Xie and Xiaoqing Ellen Tan and Po-Yao Huang and Russell Howes and Vasu Sharma and Shang-Wen Li and Gargi Ghosh and Luke Zettlemoyer and Christoph Feichtenhofer},
+      year={2023},
+      eprint={2309.16671},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}
+```

clip/facebook/metaclip-l14-400m/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|endoftext|>": 49407,
+  "<|startoftext|>": 49406
+}

clip/facebook/metaclip-l14-400m/preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "CLIPProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

clip/facebook/metaclip-l14-400m/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|startoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

clip/facebook/metaclip-l14-400m/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "CLIPProcessor",
+  "tokenizer_class": "CLIPTokenizer",
+  "tokenizer_file": "/Users/georgebredis/.cache/huggingface/hub/models--openai--clip-vit-base-patch32/snapshots/e6a30b603a447e251fdaca1c3056b2a16cdfebeb/tokenizer.json",
+  "unk_token": "<|endoftext|>"
+}

clip/laion/CLIP-ViT-L-14-DataComp.XL-s13B-b90K/open_clip_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6509f07e6fc0da68f8e1ee881bf90803f0b053d2f7ed2013cc7c3a49ac4dd3db
+size 1710639109

clip/laion/CLIP-ViT-L-14-laion2B-s32B-b82K/open_clip_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d129ed747e0ed53e82dfcc140382b51be66b56e6a9bdc3258afd2846e3bb019
+size 1710517748

clip/openai/clip-vit-large-patch14/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1a17cdbe0f36fec524f5cafb1c261ea3bbbc13e346e0f74fc9eb0460dedd0d3
+size 1710671599

clip/openai/clip-vit-large-patch14/tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f154e925c18270d662d28f6261523c2ff6e80f1f05292cb034db41d5951c7a4
+size 1711114176