CODA

Closed weights The University of Hong Kong,Sun Yat-sen University,Shanghai AI Lab 246.9M parameters May 2021

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,Sun Yat-sen University,Shanghai AI Lab
Organisation type
Academia,Academia,Academia
Country
Hong Kong, China
Published
31 May 2021
Authors
Lin Zheng, Zhiyong Wu, Lingpeng Kong

What it does

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

Domain
Language
Task
Language modeling, Translation

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
246.9M

Table 1

Training data
103,000,000 tokens

"Wikitext-103 [...] consists of articles from Wikipedia with the token number around 103M/218K/246K for the training/validation/testing splits respectively."

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

MIT for code: https://github.com/LZhengisme/CODA

How it is classified

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

Record confidence
Confident
Citations
3
Benchmark data
CODA

Sources

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

Reference
Cascaded Head-colliding Attention
Last updated
1 December 2025

What the numbers mean

Background

CODA was published by The University of Hong Kong,Sun Yat-sen University,Shanghai AI Lab, in the country recorded as Hong Kong, during May 2021. The publishing organisation is categorised as academia,Academia,Academia.

It works in the domain of Language, and is recorded as performing the task of language modeling, Translation.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

What went into building it

Training consumed a corpus of around 103,000,000 tokens of text.

Answers

CODA — common questions

01

CODA— who created it?

It was published by The University of Hong Kong,Sun Yat-sen University,Shanghai AI Lab, based in Hong Kong, an organisation categorised as academia,Academia,Academia.

02

CODA— when was it released?

It was published in May 2021. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

03

CODA— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling, Translation. These are the areas it was designed around; they describe intent rather than a hard boundary.

04

CODA— what GPU do I need to run it?

None. This 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.

05

CODA— is it open source?

No. Its weights have not been published, so it exists only as a service controlled by its owner.

06

CODA— how many parameters does it have?

It has a parameter count of 246.9M. Table 1. 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.

Source

Original publication

Record last updated 1 December 2025

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.