GPT-2 + Progressive LRD

Closed weights Huawei,Huawei Noah's Ark Lab 31M parameters October 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
Huawei,Huawei Noah's Ark Lab
Organisation type
Industry,Industry
Country
China
Published
12 October 2022
Authors
Habib Hajimolahoseini, Walid Ahmed, Mehdi Rezagholizadeh, Vahid Partovinia, Yang Liu

What it does

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

Domain
Language
Task
Language modeling/generation
Base model
GPT-2 (124M)

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
31M

Table 2 They compressed GPT-2 (124M parameters) to 31M parameters

Training data
tokens

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
7.9 × 10²⁰ FLOP

base model training compute estimation: 7.936 × 10^20 FLOP __________ In the Algorithmic progress paper the estimation was 6.2 × 10^19 FLOP

How it was established
Comparison with other models

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.

Record confidence
Speculative
Benchmark data
Progressive LRD

Sources

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

Reference
Strategies for Applying Low Rank Decomposition to Transformer-Based Models
Last updated
28 November 2025

What the numbers mean

Where it came from

GPT-2 + Progressive LRD was published by Huawei,Huawei Noah's Ark Lab, in the country recorded as China, during October 2022. The publishing organisation is categorised as industry,Industry.

It works in the domain of Language, and is recorded as performing the task of language modeling/generation.

Its starting point was an existing base model, GPT-2 (124M). That is why it shares the base model's general shape and size.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

Training and provenance

The training run consumed about 7.9 × 10²⁰ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Answers

GPT-2 + Progressive LRD — common questions

01

GPT-2 + Progressive LRD— how many parameters does it have?

It has a parameter count of 31M. Table 2 They compressed GPT-2 (124M parameters) to 31M 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.

02

GPT-2 + Progressive LRD— who created it?

It was published by Huawei,Huawei Noah's Ark Lab, based in China, an organisation categorised as industry,Industry.

03

GPT-2 + Progressive LRD— when was it released?

It was published in October 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.

04

GPT-2 + Progressive LRD— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling/generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

05

GPT-2 + Progressive LRD— how much compute was used to train it?

Training consumed around 7.9 × 10²⁰ 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

GPT-2 + Progressive LRD— 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

GPT-2 + Progressive LRD— 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 28 November 2025

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.