Transformer-XL + AutoDropout (PTB)

Closed weights Google Research 24M parameters January 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
Google Research
Organisation type
Industry
Country
United States of America
Published
5 January 2021
Authors
Hieu Pham, Quoc V. Le

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
24M

"We use the same model size as specified by Dai et al. (2019)."

Training data
tokens
Epochs
192

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
5.8 × 10¹⁶ FLOP

"We train every configuration from scratch for 160,000 steps, using a batch size of 16 and a segment length of 70" Total tokens: 160000*16*70=179200000 Epochs: 179200000/929000=192 Training flop: 6*24000000*179200000=2.58048e+16 GPU hour estimate: 40*60*4*45000000000000*0.3=1.296e+17 Geometric mean: 57829941034035304

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
Google TPU v2
Chips used
4
Wall-clock time
1 hours
Power draw
2.3 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

404: https://github.com/google-research/google-research/tree/master/auto_dropout

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
63
Benchmark data
Transformer-XL + AutoDropout (PTB)

Sources

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

Reference
AutoDropout: Learning Dropout Patterns to Regularize Deep Networks
Last updated
25 May 2026

What the numbers mean

Background

Transformer-XL + AutoDropout (PTB) was published by Google Research, in the country recorded as United States of America, during January 2021. It comes out of an organisation categorised as industry.

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

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

How it was trained

Training it took a computation budget of roughly 5.8 × 10¹⁶ FLOP, on hardware recorded as Google TPU v2. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Answers

Transformer-XL + AutoDropout (PTB) — common questions

01

Transformer-XL + AutoDropout (PTB)— who created it?

It was published by Google Research, based in United States of America, an organisation categorised as industry.

02

Transformer-XL + AutoDropout (PTB)— when was it released?

It was published in January 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

Transformer-XL + AutoDropout (PTB)— what is it used for?

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

04

Transformer-XL + AutoDropout (PTB)— how much compute was used to train it?

Training consumed around 5.8 × 10¹⁶ FLOP, on hardware recorded as Google TPU v2. 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.

05

Transformer-XL + AutoDropout (PTB)— 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.

06

Transformer-XL + AutoDropout (PTB)— is it open source?

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

07

Transformer-XL + AutoDropout (PTB)— how many parameters does it have?

It has a parameter count of 24M. "We use the same model size as specified by Dai et al. (2019).". 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 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.