GPT2-Large+LHOPT

Closed weights OpenAI 760M parameters June 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
OpenAI
Organisation type
Industry
Country
United States of America
Published
2 June 2021
Authors
Diogo Almeida, Clemens Winter, Jie Tang, Wojciech Zaremba

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 (774M)

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
760M
Training data
103,000,000 tokens
Epochs
1
Batch size
13,000

Figure 3

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
5 × 10²¹ FLOP

base model compute (speculative confidence) 4.9536e+21 FLOP + fine-tune compute 4.6968e+17 FLOP = 4.9540697e+21 FLOP ________ estimation from the Arithmetic progress paper: 1.6E+21 FLOP

How it was established
Operation counting
Fine-tuning compute
4.7 × 10¹⁷ FLOP

6 FLOP / parameter / token * 760000000 parameters * 103000000 tokens * 1 epoch = 4.6968e+17 FLOP

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 for the optimizer but no training code for this model: https://github.com/openai/LHOPT

How it is classified

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

Record confidence
Speculative
Citations
35
Benchmark data
GPT2-Large+LHOPT

Sources

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

Reference
A Generalizable Approach to Learning Optimizers
Last updated
25 May 2026

What the numbers mean

Where it came from

GPT2-Large+LHOPT was published by OpenAI, in United States of America, in June 2021. It comes out of industry.

It works in Language, and is recorded as doing language modeling/generation.

Its starting point was GPT-2 (774M) — most models at this scale are adapted from an existing base rather than built from nothing.

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

Training and provenance

Training it took roughly 5 × 10²¹ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.

It was trained on about 103,000,000 tokens of text.

Answers

GPT2-Large+LHOPT — common questions

01

What is GPT2-Large+LHOPT used for?

GPT2-Large+LHOPT works in Language, and is recorded as handling language modeling/generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

02

How much compute was used to train GPT2-Large+LHOPT?

Around 5 × 10²¹ 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.

03

What GPU do I need to run GPT2-Large+LHOPT?

None. GPT2-Large+LHOPT 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.

04

Is GPT2-Large+LHOPT open source?

No. GPT2-Large+LHOPT has not had its weights published, so it exists only as a service controlled by its owner.

05

How many parameters does GPT2-Large+LHOPT have?

GPT2-Large+LHOPT has 760M 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.

06

Who created GPT2-Large+LHOPT?

GPT2-Large+LHOPT was published by OpenAI, based in United States of America, categorised as industry.

07

When was GPT2-Large+LHOPT released?

GPT2-Large+LHOPT was published in June 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.

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.