Paragraph Vector
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
- Organisation type
- Industry
- Country
- United States of America
- Published
- 14 May 2014
- Authors
- Quoc V. Le, Tomas Mikolov
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Language modeling
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
- 32M
- Training data
- 16,500,000 tokens
75000*400+5000*400=32000000 "We learn the word vectors and paragraph vectors using 75,000 training documents" "In PV-DM, the learned vector representations have 400 dimensions for both words and documents" Paragraph embedding of dimension number of paragraphs * embedding size Word embedding of dimension |V|*embedding size Assuming vocabulary of 5000 since results are compared directly to Maas et. al., 2011
"25,000 labeled training instances, 25,000 labeled test in- stances and 50,000 unlabeled training instances."
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
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- Distributed Representations of Sentences and Documents
- Last updated
- 28 November 2025
What the numbers mean
About this model
Paragraph Vector was published by Google, in the country recorded as United States of America, during May 2014. It comes out of an organisation categorised as industry.
It works in the domain of Language, and is recorded as performing the task of language modeling.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
How it was trained
Training consumed a corpus of around 16,500,000 tokens of text.
It is tracked in the underlying dataset for one reason in particular: highly cited.
Answers
Paragraph Vector — common questions
Paragraph Vector— how many parameters does it have?
It has a parameter count of 32M. 75000*400+5000*400=32000000 "We learn the word vectors and paragraph vectors using 75,000 training documents" "In PV-DM, the learned vector representations have 400 dimensions for both words and documents" Paragraph embedding of dimension number of paragraphs * embedding size Word embedding of dimension |V|*embedding size Assuming vocabulary of 5000 since results are compared directly to Maas et. al., 2011. 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.
Paragraph Vector— who created it?
It was published by Google, based in United States of America, an organisation categorised as industry.
Paragraph Vector— when was it released?
It was published in May 2014. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
Paragraph Vector— what is it used for?
It works in the domain of Language, and is recorded as handling the task of language modeling. These are the areas it was designed around; they describe intent rather than a hard boundary.
Paragraph Vector— 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.
Paragraph Vector— is it open source?
The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
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.