AWD-FWM (WT2)

Closed weights IDSIA,Microsoft Research 37M parameters November 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
IDSIA,Microsoft Research
Organisation type
Academia,Industry
Country
Switzerland, United States of America
Published
16 November 2020
Authors
Imanol Schlag, Tsendsuren Munkhdalai, Jürgen Schmidhuber

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
37M

"all WT2 models have roughly 37M parameters"

Training data
2,000,000 tokens
Epochs
1,600

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
7.1 × 10¹⁷ FLOP

6 FLOP / parameter / token * 37000000 parameters * 2000000 tokens * 1600 epochs = 7.104e+17 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, repo license is MIT: https://github.com/ischlag/Fast-Weight-Memory-public/tree/main/language-modelling/fwm train and eval code: https://github.com/ischlag/Fast-Weight-Memory-public/blob/main/language-modelling/fwm/FWM-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
64
Benchmark data
AWD-FWM (WT2)

Sources

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

Reference
Learning Associative Inference Using Fast Weight Memory
Last updated
25 May 2026

What the numbers mean

Background

AWD-FWM (WT2) was published by IDSIA,Microsoft Research, in the country recorded as Switzerland, during November 2020. It comes out of an organisation categorised as academia,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.

Training and provenance

Training it took a computation budget of roughly 7.1 × 10¹⁷ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Training consumed a corpus of around 2,000,000 tokens of text.

Answers

AWD-FWM (WT2) — common questions

01

AWD-FWM (WT2)— how much compute was used to train it?

Training consumed around 7.1 × 10¹⁷ 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.

02

AWD-FWM (WT2)— 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.

03

AWD-FWM (WT2)— is it open source?

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

04

AWD-FWM (WT2)— how many parameters does it have?

It has a parameter count of 37M. "all WT2 models have roughly 37M 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.

05

AWD-FWM (WT2)— who created it?

It was published by IDSIA,Microsoft Research, based in Switzerland, an organisation categorised as academia,Industry.

06

AWD-FWM (WT2)— when was it released?

It was published in November 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.

07

AWD-FWM (WT2)— 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.

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.