RNTN
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
- Stanford University
- Organisation type
- Academia
- Country
- United States of America
- Published
- 1 October 2013
- Authors
- R. Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D. Manning, A. Ng, Christopher Potts
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Sentiment classification
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.
- Training data
- 155,063 tokens
"The sentences in the treebank were split into a train (8544), dev (1101) and test splits (2210)" Training data: 215154*(8544/11855)=155063
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
- 1.4 × 10¹⁶ FLOP
"The RNTN would usually achieve its best performance on the dev set after training for 3 - 5 hours."
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Wall-clock time
- 5 hours
The RNTN would usually achieve its best performance on the dev set after training for 3 - 5 hours.
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.
- Why it is tracked
- Highly cited
- Record confidence
- Likely
Sources
Where this record came from and when it was last checked.
- Reference
- Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
- Last updated
- 28 November 2025
What the numbers mean
What this model is
RNTN was published by Stanford University, in United States of America, in October 2013. academia is the category the publisher falls under.
It works in Language, and is recorded as doing sentiment classification.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
What went into building it
Training it took roughly 1.4 × 10¹⁶ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.
The training set ran to roughly 155,063 tokens.
It is tracked in the underlying dataset for one reason in particular: highly cited.
Answers
RNTN — common questions
How much compute was used to train RNTN?
Around 1.4 × 10¹⁶ 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 RNTN?
None. RNTN 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 RNTN open source?
No. RNTN has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does RNTN have?
No parameter count has been published for RNTN, which is why no memory or speed figure appears on this page.
Who created RNTN?
RNTN was published by Stanford University, based in United States of America, categorised as academia.
When was RNTN released?
RNTN was published in October 2013. 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 RNTN used for?
RNTN works in Language, and is recorded as handling sentiment classification. 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.
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.