sontal commited on
Commit
7ea4b26
1 Parent(s): 65a35ce

add bin files

Browse files
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5e990424fa7463e56f12483c3baaf852c3de5182d975360dd4e0cd5b908603a
3
+ size 9943125667
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbf8638c4587c2473be39fd301cd0009083fc6db007bf6cb0eb25dbe4a346369
3
+ size 3486832249
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
3
+ size 1033105
vit/clip-vit-H-14-laion2B-s32B-b79K-yi-vl-6B-448/.gitattributes ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ftz filter=lfs diff=lfs merge=lfs -text
6
+ *.gz filter=lfs diff=lfs merge=lfs -text
7
+ *.h5 filter=lfs diff=lfs merge=lfs -text
8
+ *.joblib filter=lfs diff=lfs merge=lfs -text
9
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
10
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
11
+ *.model filter=lfs diff=lfs merge=lfs -text
12
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
13
+ *.npy filter=lfs diff=lfs merge=lfs -text
14
+ *.npz filter=lfs diff=lfs merge=lfs -text
15
+ *.onnx filter=lfs diff=lfs merge=lfs -text
16
+ *.ot filter=lfs diff=lfs merge=lfs -text
17
+ *.parquet filter=lfs diff=lfs merge=lfs -text
18
+ *.pb filter=lfs diff=lfs merge=lfs -text
19
+ *.pickle filter=lfs diff=lfs merge=lfs -text
20
+ *.pkl filter=lfs diff=lfs merge=lfs -text
21
+ *.pt filter=lfs diff=lfs merge=lfs -text
22
+ *.pth filter=lfs diff=lfs merge=lfs -text
23
+ *.rar filter=lfs diff=lfs merge=lfs -text
24
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
26
+ *.tflite filter=lfs diff=lfs merge=lfs -text
27
+ *.tgz filter=lfs diff=lfs merge=lfs -text
28
+ *.wasm filter=lfs diff=lfs merge=lfs -text
29
+ *.xz filter=lfs diff=lfs merge=lfs -text
30
+ *.zip filter=lfs diff=lfs merge=lfs -text
31
+ *.zst filter=lfs diff=lfs merge=lfs -text
32
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
vit/clip-vit-H-14-laion2B-s32B-b79K-yi-vl-6B-448/README.md ADDED
@@ -0,0 +1,165 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ widget:
4
+ - src: >-
5
+ https://huggingface.co/datasets/mishig/sample_images/resolve/main/cat-dog-music.png
6
+ candidate_labels: playing music, playing sports
7
+ example_title: Cat & Dog
8
+ library_name: open_clip
9
+ pipeline_tag: zero-shot-image-classification
10
+ ---
11
+ # Model Card for CLIP ViT-H/14 - LAION-2B
12
+
13
+ # Table of Contents
14
+
15
+ 1. [Model Details](#model-details)
16
+ 2. [Uses](#uses)
17
+ 3. [Training Details](#training-details)
18
+ 4. [Evaluation](#evaluation)
19
+ 5. [Acknowledgements](#acknowledgements)
20
+ 6. [Citation](#citation)
21
+ 7. [How To Get Started With the Model](#how-to-get-started-with-the-model)
22
+
23
+
24
+ # Model Details
25
+
26
+ ## Model Description
27
+
28
+ A CLIP ViT-H/14 model trained with the LAION-2B English subset of LAION-5B (https://laion.ai/blog/laion-5b/) using OpenCLIP (https://github.com/mlfoundations/open_clip).
29
+
30
+ Model training done by Romain Beaumont on the [stability.ai](https://stability.ai/) cluster.
31
+
32
+ # Uses
33
+
34
+ As per the original [OpenAI CLIP model card](https://github.com/openai/CLIP/blob/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1/model-card.md), this model is intended as a research output for research communities. We hope that this model will enable researchers to better understand and explore zero-shot, arbitrary image classification. We also hope it can be used for interdisciplinary studies of the potential impact of such model.
35
+
36
+ The OpenAI CLIP paper includes a discussion of potential downstream impacts to provide an example for this sort of analysis. Additionally, the LAION-5B blog (https://laion.ai/blog/laion-5b/) and upcoming paper include additional discussion as it relates specifically to the training dataset.
37
+
38
+ ## Direct Use
39
+
40
+ Zero-shot image classification, image and text retrieval, among others.
41
+
42
+ ## Downstream Use
43
+
44
+ Image classification and other image task fine-tuning, linear probe image classification, image generation guiding and conditioning, among others.
45
+
46
+ ## Out-of-Scope Use
47
+
48
+ As per the OpenAI models,
49
+
50
+ **Any** deployed use case of the model - whether commercial or not - is currently out of scope. Non-deployed use cases such as image search in a constrained environment, are also not recommended unless there is thorough in-domain testing of the model with a specific, fixed class taxonomy. This is because our safety assessment demonstrated a high need for task specific testing especially given the variability of CLIP’s performance with different class taxonomies. This makes untested and unconstrained deployment of the model in any use case currently potentially harmful.
51
+
52
+ Certain use cases which would fall under the domain of surveillance and facial recognition are always out-of-scope regardless of performance of the model. This is because the use of artificial intelligence for tasks such as these can be premature currently given the lack of testing norms and checks to ensure its fair use.
53
+
54
+ Since the model has not been purposefully trained in or evaluated on any languages other than English, its use should be limited to English language use cases.
55
+
56
+ Further the above notice, the LAION-5B dataset used in training of these models has additional considerations, see below.
57
+
58
+ # Training Details
59
+
60
+ ## Training Data
61
+
62
+ This model was trained with the 2 Billion sample English subset of LAION-5B (https://laion.ai/blog/laion-5b/).
63
+
64
+ **IMPORTANT NOTE:** The motivation behind dataset creation is to democratize research and experimentation around large-scale multi-modal model training and handling of uncurated, large-scale datasets crawled from publically available internet. Our recommendation is therefore to use the dataset for research purposes. Be aware that this large-scale dataset is uncurated. Keep in mind that the uncurated nature of the dataset means that collected links may lead to strongly discomforting and disturbing content for a human viewer. Therefore, please use the demo links with caution and at your own risk. It is possible to extract a “safe” subset by filtering out samples based on the safety tags (using a customized trained NSFW classifier that we built). While this strongly reduces the chance for encountering potentially harmful content when viewing, we cannot entirely exclude the possibility for harmful content being still present in safe mode, so that the warning holds also there. We think that providing the dataset openly to broad research and other interested communities will allow for transparent investigation of benefits that come along with training large-scale models as well as pitfalls and dangers that may stay unreported or unnoticed when working with closed large datasets that remain restricted to a small community. Providing our dataset openly, we however do not recommend using it for creating ready-to-go industrial products, as the basic research about general properties and safety of such large-scale models, which we would like to encourage with this release, is still in progress.
65
+
66
+ ## Training Procedure
67
+
68
+ Please see [training notes](https://docs.google.com/document/d/1EFbMLRWSSV0LUf9Du1pWzWqgeiIRPwEWX2s1C6mAk5c) and [wandb logs](https://wandb.ai/rom1504/eval_openclip/reports/H-14--VmlldzoyNDAxODQ3).
69
+
70
+ # Evaluation
71
+
72
+ Evaluation done with code in the [LAION CLIP Benchmark suite](https://github.com/LAION-AI/CLIP_benchmark).
73
+
74
+ ## Testing Data, Factors & Metrics
75
+
76
+ ### Testing Data
77
+
78
+ The testing is performed with VTAB+ (A combination of VTAB (https://arxiv.org/abs/1910.04867) w/ additional robustness datasets) for classification and COCO and Flickr for retrieval.
79
+
80
+ **TODO** - more detail
81
+
82
+ ## Results
83
+
84
+ The model achieves a 78.0 zero-shot top-1 accuracy on ImageNet-1k.
85
+
86
+ An initial round of benchmarks have been performed on a wider range of datasets, currently viewable at https://github.com/LAION-AI/CLIP_benchmark/blob/main/benchmark/results.ipynb
87
+
88
+ **TODO** - create table for just this model's metrics.
89
+
90
+ # Acknowledgements
91
+
92
+ Acknowledging [stability.ai](https://stability.ai/) for the compute used to train this model.
93
+
94
+ # Citation
95
+
96
+ **BibTeX:**
97
+
98
+ LAION-5B
99
+ ```bibtex
100
+ @inproceedings{schuhmann2022laionb,
101
+ title={{LAION}-5B: An open large-scale dataset for training next generation image-text models},
102
+ author={Christoph Schuhmann and
103
+ Romain Beaumont and
104
+ Richard Vencu and
105
+ Cade W Gordon and
106
+ Ross Wightman and
107
+ Mehdi Cherti and
108
+ Theo Coombes and
109
+ Aarush Katta and
110
+ Clayton Mullis and
111
+ Mitchell Wortsman and
112
+ Patrick Schramowski and
113
+ Srivatsa R Kundurthy and
114
+ Katherine Crowson and
115
+ Ludwig Schmidt and
116
+ Robert Kaczmarczyk and
117
+ Jenia Jitsev},
118
+ booktitle={Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
119
+ year={2022},
120
+ url={https://openreview.net/forum?id=M3Y74vmsMcY}
121
+ }
122
+ ```
123
+
124
+ OpenAI CLIP paper
125
+ ```
126
+ @inproceedings{Radford2021LearningTV,
127
+ title={Learning Transferable Visual Models From Natural Language Supervision},
128
+ author={Alec Radford and Jong Wook Kim and Chris Hallacy and A. Ramesh and Gabriel Goh and Sandhini Agarwal and Girish Sastry and Amanda Askell and Pamela Mishkin and Jack Clark and Gretchen Krueger and Ilya Sutskever},
129
+ booktitle={ICML},
130
+ year={2021}
131
+ }
132
+ ```
133
+
134
+ OpenCLIP software
135
+ ```
136
+ @software{ilharco_gabriel_2021_5143773,
137
+ author = {Ilharco, Gabriel and
138
+ Wortsman, Mitchell and
139
+ Wightman, Ross and
140
+ Gordon, Cade and
141
+ Carlini, Nicholas and
142
+ Taori, Rohan and
143
+ Dave, Achal and
144
+ Shankar, Vaishaal and
145
+ Namkoong, Hongseok and
146
+ Miller, John and
147
+ Hajishirzi, Hannaneh and
148
+ Farhadi, Ali and
149
+ Schmidt, Ludwig},
150
+ title = {OpenCLIP},
151
+ month = jul,
152
+ year = 2021,
153
+ note = {If you use this software, please cite it as below.},
154
+ publisher = {Zenodo},
155
+ version = {0.1},
156
+ doi = {10.5281/zenodo.5143773},
157
+ url = {https://doi.org/10.5281/zenodo.5143773}
158
+ }
159
+ ```
160
+
161
+ # How to Get Started with the Model
162
+
163
+ Use the code below to get started with the model.
164
+
165
+ ** TODO ** - Hugging Face transformers, OpenCLIP, and timm getting started snippets
vit/clip-vit-H-14-laion2B-s32B-b79K-yi-vl-6B-448/config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "clip-vit-H-14-laion2B-s32B-b79K-yi-vl-6B-448",
3
+ "architectures": [
4
+ "CLIPVisionModel"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "dropout": 0.0,
8
+ "hidden_act": "gelu",
9
+ "hidden_size": 1280,
10
+ "image_size": 448,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5120,
14
+ "layer_norm_eps": 1e-05,
15
+ "model_type": "clip_vision_model",
16
+ "num_attention_heads": 16,
17
+ "num_channels": 3,
18
+ "num_hidden_layers": 32,
19
+ "patch_size": 14,
20
+ "projection_dim": 1024,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.34.0"
23
+ }
vit/clip-vit-H-14-laion2B-s32B-b79K-yi-vl-6B-448/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
vit/clip-vit-H-14-laion2B-s32B-b79K-yi-vl-6B-448/open_clip_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_cfg": {
3
+ "embed_dim": 1024,
4
+ "vision_cfg": {
5
+ "image_size": 224,
6
+ "layers": 32,
7
+ "width": 1280,
8
+ "head_width": 80,
9
+ "patch_size": 14
10
+ },
11
+ "text_cfg": {
12
+ "context_length": 77,
13
+ "vocab_size": 49408,
14
+ "width": 1024,
15
+ "heads": 16,
16
+ "layers": 24
17
+ }
18
+ },
19
+ "preprocess_cfg": {
20
+ "mean": [
21
+ 0.48145466,
22
+ 0.4578275,
23
+ 0.40821073
24
+ ],
25
+ "std": [
26
+ 0.26862954,
27
+ 0.26130258,
28
+ 0.27577711
29
+ ]
30
+ }
31
+ }
vit/clip-vit-H-14-laion2B-s32B-b79K-yi-vl-6B-448/open_clip_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a78ef8e8c73fd0df621682e7a8e8eb36c6916cb3c16b291a082ecd52ab79cc4
3
+ size 3944692325
vit/clip-vit-H-14-laion2B-s32B-b79K-yi-vl-6B-448/preprocessor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": 448,
3
+ "do_center_crop": true,
4
+ "do_normalize": true,
5
+ "do_resize": true,
6
+ "feature_extractor_type": "CLIPFeatureExtractor",
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "resample": 3,
18
+ "size": 448
19
+ }
vit/clip-vit-H-14-laion2B-s32B-b79K-yi-vl-6B-448/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89baa615a9db2288beca98aa76109346dcaaa7919ec4e66edb876c7a3be52286
3
+ size 2527168934
vit/clip-vit-H-14-laion2B-s32B-b79K-yi-vl-6B-448/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|endoftext|>"}
vit/clip-vit-H-14-laion2B-s32B-b79K-yi-vl-6B-448/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
vit/clip-vit-H-14-laion2B-s32B-b79K-yi-vl-6B-448/tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "unk_token": {
3
+ "content": "<|endoftext|>",
4
+ "single_word": false,
5
+ "lstrip": false,
6
+ "rstrip": false,
7
+ "normalized": true,
8
+ "__type": "AddedToken"
9
+ },
10
+ "bos_token": {
11
+ "content": "<|startoftext|>",
12
+ "single_word": false,
13
+ "lstrip": false,
14
+ "rstrip": false,
15
+ "normalized": true,
16
+ "__type": "AddedToken"
17
+ },
18
+ "eos_token": {
19
+ "content": "<|endoftext|>",
20
+ "single_word": false,
21
+ "lstrip": false,
22
+ "rstrip": false,
23
+ "normalized": true,
24
+ "__type": "AddedToken"
25
+ },
26
+ "pad_token": "<|endoftext|>",
27
+ "add_prefix_space": false,
28
+ "errors": "replace",
29
+ "do_lower_case": true,
30
+ "name_or_path": "openai/clip-vit-base-patch32",
31
+ "model_max_length": 77,
32
+ "special_tokens_map_file": "./special_tokens_map.json",
33
+ "tokenizer_class": "CLIPTokenizer"
34
+ }
vit/clip-vit-H-14-laion2B-s32B-b79K-yi-vl-6B-448/vocab.json ADDED
The diff for this file is too large to render. See raw diff