Duplicate from apple/DFN2B-CLIP-ViT-L-14-39B

Co-authored-by: Alex Fang <[email protected]>

.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

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.

README.md

@@ -0,0 +1,77 @@
+---
+license: apple-amlr
+license_name: apple-sample-code-license
+license_link: LICENSE
+---
+
+A CLIP (Contrastive Language-Image Pre-training) model trained on DFN-2B. 
+Data Filtering Networks (DFNs) are small networks used to automatically filter large pools of uncurated data. 
+This model was trained on 2B images that were filtered from a pool of 12.8B uncurated image-text pairs 
+(12.8B image-text pairs from CommonPool-12.8B).
+
+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-2b
+- **Papers:**
+  - Data Filtering Networks: https://arxiv.org/abs/2309.17425
+- **Examples Seen:** 39B
+
+
+## Model Metrics 
+| Eval Dataset                |   Metric |
+|:-----------------------|---------:|
+| ImageNet 1k            | 0.8219  |
+| Caltech-101            | 0.9500 |
+| CIFAR-10               | 0.9864   |
+| CIFAR-100              | 0.8934   |
+| CLEVR Counts           | 0.3403   |
+| CLEVR Distance         | 0.2321 |
+| Country211             | 0.3198  |
+| Describable Textures   | 0.6681  |
+| EuroSAT                | 0.6819 |
+| FGVC Aircraft          | 0.4829 |
+| Food-101               | 0.9498 |
+| GTSRB                  | 0.6329 |
+| ImageNet Sketch        | 0.7043 |
+| ImageNet v2            | 0.7570   |
+| ImageNet-A             | 0.6745   |
+| ImageNet-O             | 0.3605   |
+| ImageNet-R             | 0.9184 |
+| KITTI Vehicle Distance | 0.2391 |
+| MNIST                  | 0.8745   |
+| ObjectNet              | 0.7477 |
+| Oxford Flowers-102     | 0.8784 |
+| Oxford-IIIT Pet        | 0.9611 |
+| Pascal VOC 2007        | 0.8472  |
+| PatchCamelyon          | 0.6418  |
+| Rendered SST2          | 0.5815 |
+| RESISC45               | 0.7300 |
+| Stanford Cars          | 0.9465 |
+| STL-10                 | 0.9889 |
+| SUN397                 | 0.7594 |
+| SVHN                   | 0.6573 |
+| Flickr                 | 0.8467   |
+| MSCOCO                 | 0.5957 |
+| WinoGAViL              | 0.5551 |
+| iWildCam               | 0.1857  |
+| Camelyon17             | 0.6540 |
+| FMoW                   | 0.1824 |
+| Dollar Street          | 0.6822 |
+| GeoDE                  | 0.9253  |
+| **Average**                | **0.68039** |
+
+## 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}
+}
+
+```

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": 768,
+  "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": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "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": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "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": 49408
+  },
+  "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": "gelu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "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,
+    "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": 24,
+    "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
+  }
+}

open_clip_config.json

@@ -0,0 +1,30 @@
+{
+  "model_cfg": {
+    "embed_dim": 768,
+    "vision_cfg": {
+      "image_size": 224,
+      "layers": 24,
+      "width": 1024,
+      "patch_size": 14
+    },
+    "text_cfg": {
+      "context_length": 77,
+      "vocab_size": 49408,
+      "width": 768,
+      "heads": 12,
+      "layers": 12
+    }
+  },
+  "preprocess_cfg": {
+    "mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ]
+  }
+}

open_clip_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2f724646a73b4cd392e5bb41dae589e17ba52dab83006457dddca739d3e2cf9
+size 1710615301

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a831883a1387cd76c23ce8ae7d07ac963ba2fcf9f63ec9eadc080e21f10fa9d
+size 1710664269

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
+  }
+}

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
+  }
+}