rorshark-vit-base by Chester Enright: Open-Weight Model

Runs On

What it takes to serve rorshark-vit-base (86M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

Precision	Weights	Memory needed	Cheapest setup	Per hour	Also fits
16-bit	0.2 GB	0.2 GB	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
8-bit	0.1 GB	0.1 GB	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
4-bit	0.0 GB	0.1 GB	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00

Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.

Model Card

By Chester Enright, published under apache-2.0, revision 85b973ba04fa.

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 2e-05 - trainbatchsize: 8 - evalbatchsize: 8 - lrschedulertype: linear - numepochs: 5.0 - Transformers 4.36.0.dev0 - Pytorch 2.1.1+cu118 - Datasets 2.15.0 - Tokenizers 0.15.0

Read Chester Enright's full model card

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.0393 - Accuracy: 0.9923

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 1337 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0597	1.0	368	0.0546	0.9865
0.2009	2.0	736	0.0531	0.9865
0.0114	3.0	1104	0.0418	0.9904
0.0998	4.0	1472	0.0425	0.9904
0.1244	5.0	1840	0.0393	0.9923

Framework versions

Transformers 4.36.0.dev0
Pytorch 2.1.1+cu118
Datasets 2.15.0
Tokenizers 0.15.0

Configuration

Architecture: ViTForImageClassification
Layers: 12
Hidden size: 768
Feed-forward size: 3,072
Attention heads: 12
Stored precision: float32
Model type: vit

Identity and Version

Repository: amunchet/rorshark-vit-base
Publisher: Chester Enright
Task: Image classification
Modality: Image
Library: transformers
Parameters: 86M parameters
Languages: vit
Revision: 85b973ba04fa78630ebffce57bb1b784128eb9fc
First published: 2023-11-18
Last updated: 2023-11-18

Files and Weights

12 files, 343.3 MB in total. The weights are 2 files totalling 343.2 MB in bin, safetensors.

Weights2 files · 343.2 MB

Configuration6 files · 25.9 KB

Documentation1 file · 2.0 KB

Other2 files · 35.6 KB

Repository1 file · 1.5 KB

Every file

File	Type	Size	SHA-256
model.safetensors	Weights	343.2 MB	3eec7fd63f2d
training_args.bin	Weights	4.7 KB	ffcc3f59e708
all_results.json	Configuration	350 B	—
config.json	Configuration	767 B	—
eval_results.json	Configuration	203 B	—
preprocessor_config.json	Configuration	325 B	—
train_results.json	Configuration	167 B	—
trainer_state.json	Configuration	24.1 KB	—
README.md	Documentation	2.0 KB	—
runs/Nov18_20-49-17_gpu2/events.out.tfevents.1700340562.gpu2.60464.0	Other	35.2 KB	33e3163f81d6
runs/Nov18_20-49-17_gpu2/events.out.tfevents.1700341120.gpu2.60464.1	Other	411 B	1790db96b3f6
.gitattributes	Repository	1.5 KB	—

License and Download

License: apache-2.0
Access: Open weights, no gate
Download size: 343.2 MB

Download from Chester Enright

Released by Chester Enright through its official repository on Hugging Face. Read the license.

Built From

Derived from google/vit-base-patch16-224-in21k
Trained on (disclosed) imagefolder

Evaluations

Each result is shown as reported, with the conditions its reporter stated. None is a SAVRN measurement. A comparison lines two results up only when their configuration, unit and setup are all stated and identical.

Benchmark	Conditions	Result	Reported by	Revision	Date
imagefolder	Configuration defaultTask Image ClassificationMetric AccuracyComparison conditions not established	0.992293	amunchet Publisher reported	Evaluated revision not stated	—

Memory Requirements

Precision	Weights in memory
As published	343.2 MB
16-bit	0.2 GB
8-bit	0.1 GB
4-bit	0.0 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Compare rorshark-vit-base

nsfw_image_detection vs rorshark-vit-base

Questions About rorshark-vit-base

How much GPU memory does rorshark-vit-base need?

About 0.2 GB at 16-bit and 0.1 GB at 4-bit: the weights (86M parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run rorshark-vit-base on?

At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

Can I use rorshark-vit-base commercially?

Yes. rorshark-vit-base is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

Similar Models

Model · Image classification

nsfw_image_detection

Falcons.ai

The Fine-Tuned Vision Transformer (ViT) is a variant of the transformer encoder architecture, similar to BERT, that has been adapted for image classification tasks. This specific model, named "google/vit-base-patch16-224-in21k," is pre-trained on a substantial collection of images in a supervised manner, leveraging the ImageNet-21k dataset. The images in the pre-training dataset are resized to a resolution of 224x224 pixels, making it suitable for a wide range of image recognition tasks. During the training phase, meticulous attention was given to hyperparameter settings to ensure optimal model performance. The model was fine-tuned with a judiciously chosen batch size of 16. This choice not…

Open weights apache-2.0 86M parameters transformers

View model

Model · Image classification

gender-classification

Rizvan Dwikifirdaus

Autogenerated by HuggingPics Create your own image classifier for anything by running the demo on Google Colab. Report any issues with the demo at the github repo.

Open weights 86M parameters transformers

View model

Model · Image classification

gender-classification-2

Rizvan Dwikifirdaus

Autogenerated by HuggingPics Create your own image classifier for anything by running the demo on Google Colab. Report any issues with the demo at the github repo.

Open weights 86M parameters transformers

View model

Model · Image classification

nsfw-classifier

Giacomo Arienti

In today's digital world, user-generated content is a double-edged sword. While it fosters creativity and engagement, it also opens the door to inappropriate or illegal content being shared. Our NSFW Image Classifier is specifically designed to identify and filter out explicit images, including pornography, hentai, and sexually suggestive content, ensuring your platform remains safe, secure, and legally compliant. With more than 2M downloads, our NSFW Image Classifier has become the go-to solution for platforms looking to maintain a clean and safe environment for their users. Many developers and companies have already chosen our solution to protect their communities—will you be next? 1.…

Open weights cc-by-nc-nd-4.0 86M parameters transformers

View model

Model · Image classification

fairface_age_image_detection

Dmytro Iakubovskyi

Detects age group with about 59% accuracy based on an image. See https://www.kaggle.com/code/dima806/age-group-image-classification-vit for details.

Open weights apache-2.0 86M parameters transformers

View model

Model · Image classification

vit-age-classifier

Nate Raw

A vision transformer finetuned to classify the age of a given person's face.

Open weights 86M parameters transformers

View model