EN^2AS with performance reward
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
- Beijing Institute of Technology,University of Technology Sydney,Monash University
- Organisation type
- Academia,Academia,Academia
- Country
- China, Australia
- Published
- 22 July 2019
- Authors
- Miao Zhang, Huiqi Li, Shirui Pan, Taoping Liu, Steven Su
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Neural Architecture Search - NAS, Language modeling
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
- 23M
- Training data
- tokens
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
- Citations
- 1
- Benchmark data
- EN^2AS with performance reward
Table 2
Sources
Where this record came from and when it was last checked.
- Reference
- Efficient Novelty-Driven Neural Architecture Search
- Last updated
- 28 November 2025
What the numbers mean
About this model
EN^2AS with performance reward was published by Beijing Institute of Technology,University of Technology Sydney,Monash University, in the country recorded as China, during July 2019. The category the publisher falls under is academia,Academia,Academia.
It works in the domain of Language, and is recorded as performing the task of neural Architecture Search - NAS, Language modeling.
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
The reason it appears in this catalogue at all: sOTA improvement.
Answers
EN^2AS with performance reward — common questions
EN^2AS with performance reward— how many parameters does it have?
It has a parameter count of 23M. 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.
EN^2AS with performance reward— who created it?
It was published by Beijing Institute of Technology,University of Technology Sydney,Monash University, based in China, an organisation categorised as academia,Academia,Academia.
EN^2AS with performance reward— when was it released?
It was published in July 2019. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
EN^2AS with performance reward— what is it used for?
It works in the domain of Language, and is recorded as handling the task of neural Architecture Search - NAS, Language modeling. 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.
EN^2AS with performance reward— 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.
EN^2AS with performance reward— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
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.