HSO

Closed weights Toyota Technological Institute at Chicago 345M parameters December 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
Toyota Technological Institute at Chicago
Organisation type
Academia
Country
United States of America
Published
16 December 2021
Authors
Davis Yoshida, Kevin Gimpel

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 (355M)

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
345M
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
2.3 × 10²¹ FLOP

base model: Gpt-2 355M SOURCE: Uses pretrained GPT2 with 345M param, so impute from "Language Models are Unsupervised Multitask Learners" same "Speculative" confidence level

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
Citations
4
Benchmark data
HSO

Sources

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

Reference
Reconsidering the Past: Optimizing Hidden States in Language Models
Last updated
25 May 2026

What the numbers mean

Where it came from

HSO was published by Toyota Technological Institute at Chicago, in United States of America, in December 2021. academia is the category the publisher falls under.

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

It builds on GPT-2 (355M), which is why it shares that model's general shape and size.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

How it was trained

Training it took roughly 2.3 × 10²¹ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.

Answers

HSO — common questions

01

Who created HSO?

HSO was published by Toyota Technological Institute at Chicago, based in United States of America, categorised as academia.

02

When was HSO released?

HSO was published in December 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.

03

What is HSO used for?

HSO 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.

04

How much compute was used to train HSO?

Around 2.3 × 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.

05

What GPU do I need to run HSO?

None. HSO 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.

06

Is HSO open source?

No. HSO has not had its weights published, so it exists only as a service controlled by its owner.

07

How many parameters does HSO have?

HSO has 345M 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.

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.