EGRU (WT2)
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
- Ruhr University Bochum,Technische Universität Dresden,University of London
- Organisation type
- Academia,Academia,Academia
- Country
- Germany, United Kingdom of Great Britain and Northern Ireland
- Published
- 13 June 2022
- Authors
- Anand Subramoney, Khaleelulla Khan Nazeer, Mark Schöne, Christian Mayr, David Kappel
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- 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
- 74M
- Training data
- 2,000,000 tokens
- Epochs
- 2,500
- Batch size
- 8,576
74M Table 3
"All EGRU models were trained for 2500 epochs" size of WT2: 2M tokens Table S6 batch size 128 seq length 67
128 * 67 = 8576
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
- 2.2 × 10¹⁸ FLOP
- How it was established
- Operation counting
6 FLOP / token / parameter * 74000000 parameters * 2000000 tokens * 2500 epochs = 2.22 × 10^18 FLOP
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
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
Apache 2.0: https://github.com/Efficient-Scalable-Machine-Learning/EvNN train: https://github.com/Efficient-Scalable-Machine-Learning/EvNN/blob/main/benchmarks/lm/train.py
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
- 34
- Benchmark data
- EGRU (WT2)
Sources
Where this record came from and when it was last checked.
- Reference
- Efficient recurrent architectures through activity sparsity and sparse back-propagation through time
- Last updated
- 25 May 2026
What the numbers mean
Where it came from
EGRU (WT2) was published by Ruhr University Bochum,Technische Universität Dresden,University of London, in the country recorded as Germany, during June 2022. 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 language modeling.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Training and provenance
Producing it required arithmetic totalling around 2.2 × 10¹⁸ FLOP, on hardware recorded as NVIDIA A100. That figure measures what producing the model cost, and has no bearing on how fast it answers.
Training consumed a corpus of around 2,000,000 tokens of text.
Answers
EGRU (WT2) — common questions
EGRU (WT2)— when was it released?
It was published in June 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.
EGRU (WT2)— what is it used for?
It works in the domain of Language, and is recorded as handling the task of language modeling. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
EGRU (WT2)— how much compute was used to train it?
Training consumed around 2.2 × 10¹⁸ FLOP, on hardware recorded as 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.
EGRU (WT2)— 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.
EGRU (WT2)— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
EGRU (WT2)— how many parameters does it have?
It has a parameter count of 74M. 74M Table 3. 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.
EGRU (WT2)— who created it?
It was published by Ruhr University Bochum,Technische Universität Dresden,University of London, based in Germany, an organisation categorised as academia,Academia,Academia.
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.