SAVRN
Search Contact SAVRN

Open-weight model

toy-classification

by Iris Anderson vikasmvm/toy-classification

This is an experimental Perceiver codebase for Classification. It keeps the large setup intentionally manageable so architecture changes can be inspected before a full training run.

Parameters16,576
Context512
Weights66.8 KB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads

Runs On

What it takes to serve toy-classification (16,576 parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso fits
16-bit 0.0 GB 0.0 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 0.0 GB 0.0 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 0.0 GB 0.0 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 Iris Anderson, published under apache-2.0, revision 10fa3cd542bd.

This is an experimental Perceiver codebase for Classification. It keeps the large setup intentionally manageable so architecture changes can be inspected before a full training run. - The Python file contains the model and runnable example or training entry point. - config.json records the generated architecture settings. - trainingargs.json records the default experiment recipe. - model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint. - No benchmark score is claimed in this repository. The included configuration uses adamw with a exponential schedule. These are starting values in the script, not evidence of a completed…

Read Iris Anderson's full model card

Perceiver for Classification

Overview

This is an experimental Perceiver codebase for Classification. It keeps the large setup intentionally manageable so architecture changes can be inspected before a full training run.

Repository status

  • The Python file contains the model and runnable example or training entry point.
  • config.json records the generated architecture settings.
  • training_args.json records the default experiment recipe.
  • model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint.
  • No benchmark score is claimed in this repository.

Architecture

Item Value
Architecture Perceiver
Scale large
Attention dilated
Fusion low rank
Activation swish
Normalization batchnorm

Default experiment recipe

The included configuration uses adamw with a exponential schedule. These are starting values in the script, not evidence of a completed run. For a meaningful evaluation, train all baselines with the same data exposure, tuning budget, and random seeds.

Quick check

python model.py --help

Inspect the script's __main__ block for its generated smoke-test example. Because this is a custom implementation, generic automatic loading APIs require an explicit adapter before use.

Evaluation guidance

A useful first evaluation would use a task-specific labeled split, report the task metric across at least three seeds, and include a matched-capacity baseline. Keep training logs and environment versions with any published result.

Limitations

The initialization checkpoint has not been trained or audited for robustness, fairness, or domain transfer. The implementation should be treated as an experimental starting point. Results from a future trained checkpoint must be documented separately from the defaults shipped here.

Files

  • model.py — primary artifact
  • README.md — this documentation
  • config.json — architecture configuration
  • training_args.json — default experiment settings
  • model.safetensors — initialization checkpoint

License

Released under apache-2.0. Review the source-data terms separately when this repository is used with external datasets.

Configuration

Architecture
CustomResearchModel
Context length (tokens)
512
Layers
3
Hidden size
128
Feed-forward size
256
Attention heads
8
Model type
perceiver

Identity and Version

Repository
vikasmvm/toy-classification
Publisher
Iris Anderson
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
16,576 parameters
Languages
Not stated by the source
Revision
10fa3cd542bd8a88e60b0a456fed25d1a7d99f71
First published
2026-09-18
Last updated
2026-09-18

Files and Weights

6 files, 73.8 KB in total. The weights are 1 file totalling 66.8 KB in safetensors.

Weights1 file · 66.8 KB
Configuration3 files · 3.1 KB
Documentation1 file · 2.4 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
model.safetensorsWeights66.8 KB 4ed61401de93
config.jsonConfiguration437 B
model.pyConfiguration2.4 KB
training_args.jsonConfiguration192 B
README.mdDocumentation2.4 KB
.gitattributesRepository1.5 KB

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
66.8 KB
Download from Iris Anderson

Released by Iris Anderson through its official repository on Hugging Face. Read the license.

Memory Requirements

PrecisionWeights in memory
As published66.8 KB
16-bit0.0 GB
8-bit0.0 GB
4-bit0.0 GB

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

Questions About toy-classification

How much GPU memory does toy-classification need?

About 0 GB at 16-bit and 0 GB at 4-bit: the weights (16,576 parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run toy-classification 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 toy-classification commercially?

Yes. toy-classification 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.

What is toy-classification's context length?

512 tokens, from the maximum position embeddings in its published configuration.