Transformer-XL + RelationLM

Closed weights DeepMind,University of Oxford 124M parameters January 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
DeepMind,University of Oxford
Organisation type
Industry,Academia
Country
United Kingdom of Great Britain and Northern Ireland
Published
24 January 2022
Authors
Qi Liu, Dani Yogatama, Phil Blunsom

What it does

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

Domain
Language
Task
Language modeling/generation

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
124M

124M (Table 2) "We set the hidden size to 512 and the number of layers to 16 for all models."

Training data
103,000,000 tokens

"We set the lengths of text segment N, extended context M, and the relational memory P to (512, 512, 300), (384, 384, 800) and (768, 1536, 400) for WikiText-103, WMT19 and enwik8, respectively" -> sequence length - 512 tokens batch size 128 assuming 200000 steps (could be more): 200000*128*512 / 103000000 = 127 epochs no information about steps or epochs

Epochs
127

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.

How it was established
Operation counting

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
64
Power draw
36.1 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.

Citations
35
Benchmark data
TransformerXL+RelationLM

Sources

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

Reference
Relational Memory-Augmented Language Models
Last updated
25 May 2026

What the numbers mean

What this model is

Transformer-XL + RelationLM was published by DeepMind,University of Oxford, in the country recorded as United Kingdom of Great Britain and Northern Ireland, during January 2022. The publishing organisation is categorised as industry,Academia.

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

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

The training set ran to roughly 103,000,000 tokens of text.

Answers

Transformer-XL + RelationLM — common questions

01

Transformer-XL + RelationLM— is it open source?

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

02

Transformer-XL + RelationLM— how many parameters does it have?

It has a parameter count of 124M. 124M (Table 2) "We set the hidden size to 512 and the number of layers to 16 for all models.". 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

Transformer-XL + RelationLM— who created it?

It was published by DeepMind,University of Oxford, based in United Kingdom of Great Britain and Northern Ireland, an organisation categorised as industry,Academia.

04

Transformer-XL + RelationLM— when was it released?

It was published in January 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

Transformer-XL + RelationLM— what is it used for?

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

06

Transformer-XL + RelationLM— 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.

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.