Transformer Large + HCP

Closed weights University of Waterloo,Microsoft Research 257M parameters March 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
University of Waterloo,Microsoft Research
Organisation type
Academia,Industry
Country
Canada, United States of America
Published
21 March 2022
Authors
He Bai, Tong Wang, Alessandro Sordoni, Peng Shi

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
257M

257M

Training data
103,000,000 tokens
Epochs
38.18

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
6.1 × 10¹⁸ FLOP

80k steps (Table 1) "The input lengths are 150 for the base model and 384 for the large model." "large model: 18 layers, 16 heads, hidden size 1024 batch size 128" 6 FLOP / token / parameter * 257000000 parameters * 384 tokens per sequence * 128 sequences per batch * 80000 steps = 6.06339072 × 10^18 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 (non-commercial)

code, no license: https://github.com/richardbaihe/robustLM

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
17
Benchmark data
Transformer Large + HCP

Sources

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

Reference
Better Language Model with Hypernym Class Prediction
Last updated
25 May 2026

What the numbers mean

What this model is

Transformer Large + HCP was published by University of Waterloo,Microsoft Research, in the country recorded as Canada, during March 2022. The category the publisher falls under is academia,Industry.

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.

How it was trained

The training run consumed about 6.1 × 10¹⁸ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

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

Answers

Transformer Large + HCP — common questions

01

Transformer Large + HCP— how much compute was used to train it?

Training consumed around 6.1 × 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.

02

Transformer Large + HCP— 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

Transformer Large + HCP— is it open source?

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

04

Transformer Large + HCP— how many parameters does it have?

It has a parameter count of 257M. 257M. 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

Transformer Large + HCP— who created it?

It was published by University of Waterloo,Microsoft Research, based in Canada, an organisation categorised as academia,Industry.

06

Transformer Large + HCP— when was it released?

It was published in March 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.

07

Transformer Large + HCP— what is it used for?

It works in the domain of Language, and is recorded as handling the task of 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.

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.