T2R + Random Init

Closed weights University of Washington,Microsoft,DeepMind,Allen Institute for AI 450M parameters March 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
University of Washington,Microsoft,DeepMind,Allen Institute for AI
Organisation type
Academia,Industry,Industry,Research collective
Country
United States of America, United Kingdom of Great Britain and Northern Ireland
Published
24 March 2021
Authors
Jungo Kasai, Hao Peng, Yizhe Zhang, Dani Yogatama, Gabriel Ilharco, Nikolaos Pappas, Yi Mao, Weizhu Chen, Noah A. Smith

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
450M

450M source: https://arxiv.org/pdf/2203.12644 table 3

Training data
103,000,000 tokens

"We train the model with a batch size of about 74K tokens with a total of 286K steps" 74000*286000 / 103000000 = 205.48 epochs

Epochs
205.48
Batch size
74,000

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
2.7 × 10¹⁹ FLOP

6 FLOP / token / parameter * 450000000 parameters * 74000 tokens per batch * 286000 steps = 5.71428e+19 FLOP 125000000000000 [assumed bf16] * 98 GPU-hours * 3600 sec / hour * 0.3 [assumed utilization] = 1.323e+19 FLOP geometric mean: sqrt(5.71428e+19*1.323e+19) = 2.749544e+19

How it was established
Operation counting,Hardware

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
NVIDIA V100
Chips used
8
Chip-hours
98
Power draw
4.9 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

There's a repo but it's kind of inscrutable with no docs about T2R, not clear if the training code for this paper is in it: https://github.com/jungokasai/T2R/tree/master

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Likely
Citations
94
Benchmark data
T2R + Random Init

Sources

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

Reference
Finetuning Pretrained Transformers into RNNs
Last updated
25 May 2026

What the numbers mean

Background

T2R + Random Init was published by University of Washington,Microsoft,DeepMind,Allen Institute for AI, in United States of America, in March 2021. academia,Industry,Industry,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.

What went into building it

The training run consumed about 2.7 × 10¹⁹ FLOP, on NVIDIA V100. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

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

Answers

T2R + Random Init — common questions

01

What GPU do I need to run T2R + Random Init?

None. T2R + Random Init 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.

02

Is T2R + Random Init open source?

No. T2R + Random Init has not had its weights published, so it exists only as a service controlled by its owner.

03

How many parameters does T2R + Random Init have?

T2R + Random Init has 450M parameters. 450M source: https://arxiv.org/pdf/2203.12644 table 3. 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.

04

Who created T2R + Random Init?

T2R + Random Init was published by University of Washington,Microsoft,DeepMind,Allen Institute for AI, based in United States of America, categorised as academia,Industry,Industry,Research collective.

05

When was T2R + Random Init released?

T2R + Random Init was published in March 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.

06

What is T2R + Random Init used for?

T2R + Random Init 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.

07

How much compute was used to train T2R + Random Init?

Around 2.7 × 10¹⁹ FLOP, on NVIDIA V100. 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.

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.