laion / CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k

huggingface.co
Total runs: 839.8K
24-hour runs: 0
7-day runs: -31.0K
30-day runs: 743.2K
Model's Last Updated: November 13 2022

Introduction of CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k

Model Details of CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k

Model Card for CLIP ViT-B/32 roberta base - LAION-2B

Table of Contents

  1. Model Details
  2. Uses
  3. Training Details
  4. Evaluation
  5. Acknowledgements
  6. Citation
  7. How To Get Started With the Model

Model Details

Model Description

A CLIP ViT-B/32 roberta base 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 ).

Model training done by Romain Beaumont on the stability.ai cluster.

Uses

Direct Use

Zero-shot image classification, image and text retrieval, among others.

Downstream Use

Image classification and other image task fine-tuning, linear probe image classification, image generation guiding and conditioning, among others.

Training Details

Training Data

This model was trained with the 2 Billion sample English subset of LAION-5B ( https://laion.ai/blog/laion-5b/ ).

Training Procedure

Training with batch size 32k for 12B sample of laion2B-en, see https://wandb.ai/rom1504/open-clip/reports/clip-B-32-roberta-base--VmlldzoyOTM0NDQ3

Model is B/32 on visual side, roberta base initialized with pretrained weights on text side.

Evaluation

Evaluation done with code in the LAION CLIP Benchmark suite .

Testing Data, Factors & Metrics
Testing Data

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.

Results

The model achieves

  • imagenet 1k 61.7% (vs 62.9% for baseline)
  • mscoco 63% (vs 60.8% for baseline)
  • flickr30k 86.7% (vs 85.4% for baseline)

metrics

Acknowledgements

Acknowledging stability.ai for the compute used to train this model.

Citation

BibTeX:

In addition to forthcoming LAION-5B ( https://laion.ai/blog/laion-5b/ ) paper, please cite:

OpenAI CLIP paper

@inproceedings{Radford2021LearningTV,
  title={Learning Transferable Visual Models From Natural Language Supervision},
  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},
  booktitle={ICML},
  year={2021}
}

OpenCLIP software

@software{ilharco_gabriel_2021_5143773,
  author       = {Ilharco, Gabriel and
                  Wortsman, Mitchell and
                  Wightman, Ross and
                  Gordon, Cade and
                  Carlini, Nicholas and
                  Taori, Rohan and
                  Dave, Achal and
                  Shankar, Vaishaal and
                  Namkoong, Hongseok and
                  Miller, John and
                  Hajishirzi, Hannaneh and
                  Farhadi, Ali and
                  Schmidt, Ludwig},
  title        = {OpenCLIP},
  month        = jul,
  year         = 2021,
  note         = {If you use this software, please cite it as below.},
  publisher    = {Zenodo},
  version      = {0.1},
  doi          = {10.5281/zenodo.5143773},
  url          = {https://doi.org/10.5281/zenodo.5143773}
}

How To Get Started With the Model

https://github.com/mlfoundations/open_clip

Runs of laion CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k on huggingface.co

839.8K
Total runs
0
24-hour runs
-31.6K
3-day runs
-31.0K
7-day runs
743.2K
30-day runs

More Information About CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k huggingface.co Model

More CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k license Visit here:

https://choosealicense.com/licenses/mit

CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k huggingface.co

CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k huggingface.co is an AI model on huggingface.co that provides CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k's model effect (), which can be used instantly with this laion CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k model. huggingface.co supports a free trial of the CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k model, and also provides paid use of the CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k. Support call CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k model through api, including Node.js, Python, http.

CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k huggingface.co Url

https://huggingface.co/laion/CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k

laion CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k online free

CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k huggingface.co is an online trial and call api platform, which integrates CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k's modeling effects, including api services, and provides a free online trial of CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k, you can try CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k online for free by clicking the link below.

laion CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k online free url in huggingface.co:

https://huggingface.co/laion/CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k

CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k install

CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k is an open source model from GitHub that offers a free installation service, and any user can find CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k on GitHub to install. At the same time, huggingface.co provides the effect of CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k install, users can directly use CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k install url in huggingface.co:

https://huggingface.co/laion/CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k

Url of CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k

CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k huggingface.co Url

Provider of CLIP-ViT-B-32-roberta-base-laion2B-s12B-b32k huggingface.co

laion
ORGANIZATIONS

Other API from laion

huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated: June 07 2022
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated: May 25 2022
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated: June 25 2022
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated: November 16 2022