Transformer-XL DeFINE (141M)

Closed weights University of Washington,Allen Institute for AI 141M parameters November 2019

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
University of Washington,Allen Institute for AI
Organisation type
Academia,Research collective
Country
United States of America
Published
27 November 2019
Authors
Sachin Mehta, Rik Koncel-Kedziorski, Mohammad Rastegari, Hannaneh Hajishirzi

What it does

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

Domain
Language
Task
Language modeling
Numerical format
FP32

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
141M

Table 2b

Training data
103,000,000 tokens
Epochs
20

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
1.7 × 10¹⁸ FLOP

6 FLOP / token / parameter * 141000000 parameters * 103000000 tokens * 20 epochs [assumption based on number of epochs for LSTMs] = 1.74276e+18 FLOP _______________ older estimation: 6.2 × 10^18 (no explantion how it was calculated)

How it was established
Operation counting

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

"Compared to state-of-the-art methods including adaptive input representations, this technique results in a 6% to 20% drop in perplexity" Table 2a

Record confidence
Speculative
Citations
29
Benchmark data
Transformer-XL DeFINE (141M)

Sources

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

Reference
DeFINE: DEep Factorized INput Token Embeddings for Neural Sequence Modeling
Last updated
25 May 2026

What the numbers mean

Where it came from

Transformer-XL DeFINE (141M) was published by University of Washington,Allen Institute for AI, in United States of America, in November 2019. academia,Research collective is the category the publisher falls under.

It works in Language, and is recorded as doing language modeling.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

Training and provenance

Training it took roughly 1.7 × 10¹⁸ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.

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

The reason it appears in this catalogue at all is sOTA improvement.

Answers

Transformer-XL DeFINE (141M) — common questions

01

How many parameters does Transformer-XL DeFINE (141M) have?

Transformer-XL DeFINE (141M) has 141M parameters. Table 2b. 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.

02

Who created Transformer-XL DeFINE (141M)?

Transformer-XL DeFINE (141M) was published by University of Washington,Allen Institute for AI, based in United States of America, categorised as academia,Research collective.

03

When was Transformer-XL DeFINE (141M) released?

Transformer-XL DeFINE (141M) was published in November 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.

04

What is Transformer-XL DeFINE (141M) used for?

Transformer-XL DeFINE (141M) 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.

05

How much compute was used to train Transformer-XL DeFINE (141M)?

Around 1.7 × 10¹⁸ FLOP. 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.

06

What GPU do I need to run Transformer-XL DeFINE (141M)?

None. Transformer-XL DeFINE (141M) 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.

07

Is Transformer-XL DeFINE (141M) open source?

No. Transformer-XL DeFINE (141M) has not had its weights published, so it exists only as a service controlled by its owner.

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.