meta / swag

Supervised Weakly from hashtAGs

replicate.com
Total runs: 294
24-hour runs: 0
7-day runs: 0
30-day runs: 0
Github
Model's Last Updated: January 23 2022

Introduction of swag

Model Details of swag

Readme

SWAG: Supervised Weakly from hashtAGs

This repository contains SWAG models from the paper Revisiting Weakly Supervised Pre-Training of Visual Perception Models .

Citation

If you use the SWAG models or if the work is useful in your research, please give us a star and cite:

@misc{singh2022revisiting,
      title={Revisiting Weakly Supervised Pre-Training of Visual Perception Models}, 
      author={Singh, Mannat and Gustafson, Laura and Adcock, Aaron and Reis, Vinicius de Freitas and Gedik, Bugra and Kosaraju, Raj Prateek and Mahajan, Dhruv and Girshick, Ross and Doll{\'a}r, Piotr and van der Maaten, Laurens},
      journal={arXiv preprint arXiv:2201.08371},
      year={2022}
}
License

SWAG models are released under the CC-BY-NC 4.0 license. See LICENSE for additional details.

Pricing of swag replicate.com

Run time and cost

This model costs approximately $0.00043 to run on Replicate, or 2325 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker .

This model runs on Nvidia T4 GPU hardware . Predictions typically complete within 2 seconds.

Runs of meta swag on replicate.com

294
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs

More Information About swag replicate.com Model

swag replicate.com

swag replicate.com is an AI model on replicate.com that provides swag's model effect (Supervised Weakly from hashtAGs), which can be used instantly with this meta swag model. replicate.com supports a free trial of the swag model, and also provides paid use of the swag. Support call swag model through api, including Node.js, Python, http.

swag replicate.com Url

https://replicate.com/meta/swag

meta swag online free

swag replicate.com is an online trial and call api platform, which integrates swag's modeling effects, including api services, and provides a free online trial of swag, you can try swag online for free by clicking the link below.

meta swag online free url in replicate.com:

https://replicate.com/meta/swag

swag install

swag is an open source model from GitHub that offers a free installation service, and any user can find swag on GitHub to install. At the same time, replicate.com provides the effect of swag install, users can directly use swag installed effect in replicate.com for debugging and trial. It also supports api for free installation.

swag install url in replicate.com:

https://replicate.com/meta/swag

Url of swag

Provider of swag replicate.com

Other API from meta

replicate

An 8 billion parameter language model from Meta, fine tuned for chat completions

Total runs: 353.0M
Run Growth: 0
Growth Rate: 0.00%
Updated:April 18 2024
replicate

A 70 billion parameter language model from Meta, fine tuned for chat completions

Total runs: 149.0M
Run Growth: 0
Growth Rate: 0.00%
Updated:April 18 2024
replicate

Base version of Llama 3, an 8 billion parameter language model from Meta.

Total runs: 50.8M
Run Growth: 0
Growth Rate: 0.00%
Updated:April 18 2024
replicate

A 7 billion parameter language model from Meta, fine tuned for chat completions

Total runs: 17.5M
Run Growth: 0
Growth Rate: 0.00%
Updated:November 02 2023
replicate

A 70 billion parameter language model from Meta, fine tuned for chat completions

Total runs: 9.2M
Run Growth: 0
Growth Rate: 0.00%
Updated:September 13 2023
replicate

Meta's flagship 405 billion parameter language model, fine-tuned for chat completions

Total runs: 5.2M
Run Growth: 0
Growth Rate: 0.00%
Updated:July 23 2024
replicate

A 13 billion parameter language model from Meta, fine tuned for chat completions

Total runs: 4.8M
Run Growth: 0
Growth Rate: 0.00%
Updated:September 13 2023
replicate

Generate music from a prompt or melody

Total runs: 2.4M
Run Growth: 0
Growth Rate: 0.00%
Updated:March 28 2024
replicate

Base version of Llama 3, a 70 billion parameter language model from Meta.

Total runs: 825.5K
Run Growth: 0
Growth Rate: 0.00%
Updated:April 18 2024
replicate

A llama-3 based moderation and safeguarding language model

Total runs: 733.3K
Run Growth: 0
Growth Rate: 0.00%
Updated:May 08 2024
replicate

Base version of Llama 2 7B, a 7 billion parameter language model

Total runs: 651.1K
Run Growth: 0
Growth Rate: 0.00%
Updated:September 13 2023
replicate

Base version of Llama 2, a 70 billion parameter language model from Meta.

Total runs: 351.9K
Run Growth: 0
Growth Rate: 0.00%
Updated:September 13 2023
replicate

Base version of Llama 2 13B, a 13 billion parameter language model

Total runs: 201.7K
Run Growth: 0
Growth Rate: 0.00%
Updated:September 13 2023
replicate

A 34 billion parameter Llama tuned for coding and conversation

Total runs: 154.7K
Run Growth: 0
Growth Rate: 0.00%
Updated:January 09 2024
replicate

A 13 billion parameter Llama tuned for code completion

Total runs: 112.4K
Run Growth: 0
Growth Rate: 0.00%
Updated:September 29 2023
replicate

A 7 billion parameter Llama tuned for coding and conversation

Total runs: 65.1K
Run Growth: 0
Growth Rate: 0.00%
Updated:January 09 2024
replicate

A 13 billion parameter Llama tuned for coding and conversation

Total runs: 46.8K
Run Growth: 0
Growth Rate: 0.00%
Updated:September 07 2023
replicate

A Llama-3.1-8B pretrained model, fine-tuned for content safety classification

Total runs: 31.1K
Run Growth: 0
Growth Rate: 0.00%
Updated:December 21 2024
replicate

Detects any class given class names

Total runs: 27.6K
Run Growth: 0
Growth Rate: 0.00%
Updated:September 29 2022
replicate

Instance-Conditioned GAN

Total runs: 26.7K
Run Growth: 0
Growth Rate: 0.00%
Updated:September 25 2021
replicate

A 70 billion parameter Llama tuned for coding and conversation

Total runs: 21.9K
Run Growth: 0
Growth Rate: 0.00%
Updated:January 31 2024
replicate

A 7 billion parameter Llama tuned for coding and conversation

Total runs: 15.4K
Run Growth: 0
Growth Rate: 0.00%
Updated:September 07 2023
replicate

SAM 2: Segment Anything v2 (for Images)

Total runs: 11.5K
Run Growth: 0
Growth Rate: 0.00%
Updated:July 31 2024
replicate

A 17 billion parameter model with 128 experts

Total runs: 11.2K
Run Growth: 0
Growth Rate: 0.00%
Updated:April 06 2025
replicate

A 34 billion parameter Llama tuned for coding and conversation

Total runs: 10.0K
Run Growth: 0
Growth Rate: 0.00%
Updated:August 26 2023
replicate

A 34 billion parameter Llama tuned for coding with Python

Total runs: 6.5K
Run Growth: 0
Growth Rate: 0.00%
Updated:September 29 2023
replicate

A 13 billion parameter Llama tuned for coding with Python

Total runs: 3.9K
Run Growth: 0
Growth Rate: 0.00%
Updated:September 07 2023
replicate

A 7 billion parameter Llama tuned for coding with Python

Total runs: 3.8K
Run Growth: 0
Growth Rate: 0.00%
Updated:September 07 2023
replicate

SAM 2: Segment Anything v2 (for videos)

Total runs: 2.6K
Run Growth: 0
Growth Rate: 0.00%
Updated:August 14 2024
replicate

Cut and Learn for unsupervised object detection and instance segmentation

Total runs: 2.3K
Run Growth: 0
Growth Rate: 0.00%
Updated:February 06 2023
replicate

A 70 billion parameter Llama tuned for coding with Python

Total runs: 1.1K
Run Growth: 0
Growth Rate: 0.00%
Updated:January 30 2024
replicate

Masked-attention Mask Transformer for Universal Image Segmentation

Total runs: 658
Run Growth: 0
Growth Rate: 0.00%
Updated:February 21 2022
replicate

A Single Model for Many Visual Modalities

Total runs: 247
Run Growth: 0
Growth Rate: 0.00%
Updated:January 30 2022
replicate

A Llama-3.2-11B pretrained model, fine-tuned for content safety classification

Total runs: 153
Run Growth: 0
Growth Rate: 0.00%
Updated:December 24 2024
replicate

A 7B parameter Llama 2-based input-output safeguard model

Total runs: 19
Run Growth: 0
Growth Rate: 0.00%
Updated:December 21 2024
replicate

A 17 billion parameter model with 16 experts

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:April 06 2025