Vega v2

Closed weights Wuhan University,JD Explore Academy,Shanghai AI Lab,Nanyang Technological University,Washington University in St Louis,Chongqing University of Posts and Telecommunications,University of Sydney 6B parameters December 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
Wuhan University,JD Explore Academy,Shanghai AI Lab,Nanyang Technological University,Washington University in St Louis,Chongqing University of Posts and Telecommunications,University of Sydney
Organisation type
Academia,Academia,Academia,Academia,Academia,Academia
Country
China, Singapore, United States of America, Australia
Published
4 December 2022
Authors
Qihuang Zhong, Liang Ding, Yibing Zhan, Yu Qiao, Yonggang Wen, Li Shen, Juhua Liu, Baosheng Yu, Bo Du, Yixin Chen, Xinbo Gao, Chunyan Miao, Xiaoou Tang, Dacheng Tao

What it does

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

Domain
Language
Task
Language modeling, Question answering, Word sense disambiguation

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
6B
Training data
6,439,999,999 tokens

Training compute

The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.

Training compute
7.8 × 10²² FLOP

Pretraining took 1 month on 320 A100 (Section 3.1) 720*60*60*320*312000000000000*0.3=7.7635584e+22

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware
NVIDIA A100
Chips used
320
Wall-clock time
720 hours (30 days)
Power draw
255.9 kW

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
Unreleased

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

Highest score at SuperGLUE leaderboard version 2.0 in terms of RTE (Recognizing Textual Entailment-Accuracy)

Record confidence
Confident
Citations
42

Sources

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

Reference
Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE
Last updated
25 May 2026

What the numbers mean

Background

Vega v2 was published by Wuhan University,JD Explore Academy,Shanghai AI Lab,Nanyang Technological University,Washington University in St Louis,Chongqing University of Posts and Telecommunications,University of Sydney, in China, in December 2022. academia,Academia,Academia,Academia,Academia,Academia is the category the publisher falls under.

It works in Language, and is recorded as doing language modeling, Question answering, Word sense disambiguation.

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

How it was trained

Producing it required around 7.8 × 10²² FLOP of arithmetic, on NVIDIA A100, which is a statement about the training budget rather than about inference.

The training set ran to roughly 6,439,999,999 tokens.

Its inclusion criterion is sOTA improvement.

Answers

Vega v2 — common questions

01

Is Vega v2 open source?

No. Vega v2 has not had its weights published, so it exists only as a service controlled by its owner.

02

How many parameters does Vega v2 have?

Vega v2 has 6B parameters. 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.

03

Who created Vega v2?

Vega v2 was published by Wuhan University,JD Explore Academy,Shanghai AI Lab,Nanyang Technological University,Washington University in St Louis,Chongqing University of Posts and Telecommunications,University of Sydney, based in China, categorised as academia,Academia,Academia,Academia,Academia,Academia.

04

When was Vega v2 released?

Vega v2 was published in December 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.

05

What is Vega v2 used for?

Vega v2 works in Language, and is recorded as handling language modeling, Question answering, Word sense disambiguation. 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

How much compute was used to train Vega v2?

Around 7.8 × 10²² FLOP, on NVIDIA A100. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

07

What GPU do I need to run Vega v2?

None. Vega v2 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.