Shortformer

Closed weights University of Washington,Facebook AI Research,Allen Institute for AI 247M parameters December 2020

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,Facebook AI Research,Allen Institute for AI
Organisation type
Academia,Industry,Research collective
Country
United States of America, France
Published
31 December 2020
Authors
Ofir Press, Noah A. Smith, Mike Lewis

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
247M

247M (Table 5)

Training data
103,000,000 tokens
Epochs
205

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 × 10¹⁸ FLOP

6 FLOP / parameter / token * 247000000 parameters * 103000000 tokens * 205 epochs = 3.129243e+19 FLOP ________ earlier here was a mistake (1 OOM) from when the calculation for the Algorithmic progress paper was done previous estimation: 3.04e+18 FLOP

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
Open source

code, MIT: https://github.com/ofirpress/shortformer train: https://github.com/ofirpress/shortformer/blob/master/fairseq_cli/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
100
Benchmark data
Shortformer

Sources

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

Reference
Shortformer: Better Language Modeling using Shorter Inputs
Last updated
25 May 2026

What the numbers mean

What this model is

Shortformer was published by University of Washington,Facebook AI Research,Allen Institute for AI, in the country recorded as United States of America, during December 2020. The publishing organisation is categorised as academia,Industry,Research collective.

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.

What went into building it

The training run consumed about 3 × 10¹⁸ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Training consumed a corpus of around 103,000,000 tokens of text.

Answers

Shortformer — common questions

01

Shortformer— how many parameters does it have?

It has a parameter count of 247M. 247M (Table 5). 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

Shortformer— who created it?

It was published by University of Washington,Facebook AI Research,Allen Institute for AI, based in United States of America, an organisation categorised as academia,Industry,Research collective.

03

Shortformer— when was it released?

It was published in December 2020. 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

Shortformer— 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.

05

Shortformer— how much compute was used to train it?

Training consumed around 3 × 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

Shortformer— 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.

07

Shortformer— is it open source?

No. Its weights have not been 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.