DeBERTaV3large + KEAR

Closed weights Microsoft 418M parameters May 2022

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
Microsoft
Organisation type
Industry
Country
United States of America
Published
4 May 2022
Authors
Yichong Xu, Chenguang Zhu, Shuohang Wang, Siqi Sun, Hao Cheng, Xiaodong Liu, Jianfeng Gao, Pengcheng He, Michael Zeng, Xuedong Huang

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Language
Task
Question answering, Language modeling/generation
Base model
DeBERTaV3large

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters
418M

DeBERTaV3-large had 418M params, per Table 2

Training data
tokens
Epochs
10

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
Unreleased
Training code
Open source

no attributed license https://github.com/microsoft/KEAR?tab=readme-ov-file

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Why it is tracked
SOTA improvement

"The proposed system, Knowledgeable External Attention for commonsense Reasoning (KEAR), reaches human parity on the open CommonsenseQA research benchmark with an accuracy of 89.4\% in comparison to the human accuracy of 88.9\%." SOTA per https://paperswithcode.com/sota/common-sense-reasoning-on-commonsenseqa

Record confidence
Confident
Citations
63

Sources

Where this record came from and when it was last checked.

Reference
Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention
Last updated
25 May 2026

What the numbers mean

Background

DeBERTaV3large + KEAR was published by Microsoft, in United States of America, in May 2022. It comes out of industry.

It works in Language, and is recorded as doing question answering, Language modeling/generation.

It builds on DeBERTaV3large, which is why it shares that model's general shape and size.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

Training and provenance

The reason it appears in this catalogue at all is sOTA improvement.

Answers

DeBERTaV3large + KEAR — common questions

01

What is DeBERTaV3large + KEAR used for?

DeBERTaV3large + KEAR works in Language, and is recorded as handling question answering, Language modeling/generation. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

02

What GPU do I need to run DeBERTaV3large + KEAR?

None. DeBERTaV3large + KEAR is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

03

Is DeBERTaV3large + KEAR open source?

No. DeBERTaV3large + KEAR has not had its weights published, so it exists only as a service controlled by its owner.

04

How many parameters does DeBERTaV3large + KEAR have?

DeBERTaV3large + KEAR has 418M parameters. DeBERTaV3-large had 418M params, per Table 2. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

05

Who created DeBERTaV3large + KEAR?

DeBERTaV3large + KEAR was published by Microsoft, based in United States of America, categorised as industry.

06

When was DeBERTaV3large + KEAR released?

DeBERTaV3large + KEAR was published in May 2022. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

Source

Original publication

Record last updated 25 May 2026

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.