HSO
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
- How it was established
- Comparison with other models
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
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
Who created HSO?
HSO was published by Toyota Technological Institute at Chicago, based in United States of America, categorised as academia.
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.
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.
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.
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.
Is HSO open source?
No. HSO has not had its weights published, so it exists only as a service controlled by its owner.
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.
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.