SRU++ Large only 2 attention layers (k=5) (WT103)
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
- ASAPP
- Organisation type
- Industry
- Country
- United States of America
- Published
- 24 February 2021
- Authors
- Tao Lei
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
- 225M
- Training data
- tokens
- Epochs
- 34.08
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
- 3.6 × 10¹⁹ FLOP
- How it was established
- Hardware
11 V100 GPU days 11*24*60*60*125000000000000*0.3=3.564e+19
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 V100
- Chips used
- 8
- Wall-clock time
- 33 hours
- Power draw
- 4.9 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
code with MIT license (no script for WT103) https://github.com/asappresearch/sru/blob/master/language_model/README.md
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
- 54
- Benchmark data
- SRU++ Large only 2 attention layers (k=5)
Sources
Where this record came from and when it was last checked.
- Reference
- When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute
- Last updated
- 11 February 2026
What the numbers mean
Background
SRU++ Large only 2 attention layers (k=5) (WT103) was published by ASAPP, in United States of America, in February 2021. It comes out of industry.
It works in Language, and is recorded as doing 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
Training it took roughly 3.6 × 10¹⁹ FLOP of computation, on NVIDIA V100 — a measure of what producing the model cost, not of how fast it answers.
Answers
SRU++ Large only 2 attention layers (k=5) (WT103) — common questions
How many parameters does SRU++ Large only 2 attention layers (k=5) (WT103) have?
SRU++ Large only 2 attention layers (k=5) (WT103) has 225M 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.
Who created SRU++ Large only 2 attention layers (k=5) (WT103)?
SRU++ Large only 2 attention layers (k=5) (WT103) was published by ASAPP, based in United States of America, categorised as industry.
When was SRU++ Large only 2 attention layers (k=5) (WT103) released?
SRU++ Large only 2 attention layers (k=5) (WT103) was published in February 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.
What is SRU++ Large only 2 attention layers (k=5) (WT103) used for?
SRU++ Large only 2 attention layers (k=5) (WT103) works in Language, and is recorded as handling 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.
How much compute was used to train SRU++ Large only 2 attention layers (k=5) (WT103)?
Around 3.6 × 10¹⁹ FLOP, on NVIDIA V100. 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.
What GPU do I need to run SRU++ Large only 2 attention layers (k=5) (WT103)?
None. SRU++ Large only 2 attention layers (k=5) (WT103) 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.
Is SRU++ Large only 2 attention layers (k=5) (WT103) open source?
No. SRU++ Large only 2 attention layers (k=5) (WT103) has not had its weights 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.