KeAP

Closed weights The University of Hong Kong,ByteDance,JancsiTech,OPPO HealthLab January 2023

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
The University of Hong Kong,ByteDance,JancsiTech,OPPO HealthLab
Organisation type
Academia,Industry,Industry,Industry
Country
Hong Kong, China
Published
30 January 2023
Authors
Hong-Yu Zhou, Yunxiang Fu, Zhicheng Zhang, Cheng Bian, Yizhou Yu

What it does

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

Domain
Biology
Task
Proteins, Protein representation learning

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.

Training data
36,000,000 tokens

"ProteinKG25 (Zhang et al., 2022) provides a knowledge graph that consists of approximately five million triplets, with nearly 600k protein, 50k attribute terms, and 31 relation terms included" Assuming the relation and attribute terms are ~5 tokens and proteins are ~300 tokens 5000000*305=1525000000

How it is classified

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

Record confidence
Likely
Citations
11

Sources

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

Reference
Protein Representation Learning via Knowledge Enhanced Primary Structure Modeling
Last updated
25 May 2026

What the numbers mean

Where it came from

KeAP was published by The University of Hong Kong,ByteDance,JancsiTech,OPPO HealthLab, in Hong Kong, in January 2023. It comes out of academia,Industry,Industry,Industry.

It works in Biology, and is recorded as doing proteins, Protein representation learning.

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

What went into building it

The training set ran to roughly 36,000,000 tokens.

Answers

KeAP — common questions

01

Is KeAP open source?

The licensing for KeAP was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

02

How many parameters does KeAP have?

No parameter count has been published for KeAP, which is why no memory or speed figure appears on this page.

03

Who created KeAP?

KeAP was published by The University of Hong Kong,ByteDance,JancsiTech,OPPO HealthLab, based in Hong Kong, categorised as academia,Industry,Industry,Industry.

04

When was KeAP released?

KeAP was published in January 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

05

What is KeAP used for?

KeAP works in Biology, and is recorded as handling proteins, Protein representation learning. 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.

06

What GPU do I need to run KeAP?

None. KeAP 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.

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.