Dropout-LSTM+Noise(Bernoulli) (WT2)
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
- Columbia University,New York University (NYU),Princeton University
- Organisation type
- Academia,Academia,Academia
- Country
- United States of America
- Published
- 3 May 2018
- Authors
- Adji B. Dieng, Rajesh Ranganath, Jaan Altosaar, David M. Blei
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Language modeling
- Numerical format
- FP32
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
- 51M
- Training data
- 2,000,000 tokens
- Epochs
- 200
"The large network has 2 layers with 1500 hidden units each. This leads to a model complexity of 51 million parameters."
"We train the models using truncated backpropagation through time with average stochastic gradient descent (Polyak & Juditsky, 1992) for a maximum of 200 epochs"
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
- 1.3 × 10¹⁷ FLOP
- How it was established
- Operation counting
6 FLOP / parameter / token * 51000000 parameters * 2000000 tokens * 200 epochs = 1.224e+17 FLOP 'Likely' confidence because I am not very sure that 51M paramters and 200 epochs relate to WT-2 model, but it is very likely
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
"The source code is available upon request."
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
- SOTA improvement
- Record confidence
- Likely
- Citations
- 27
- Benchmark data
- Dropout-LSTM+Noise(Bernoulli) (WT2)
this is the best model in this paper per Table 4 "On language modeling benchmarks, Noisin improves over dropout by as much as 12.2% on the Penn Treebank and 9.4% on the Wikitext-2 dataset"
Sources
Where this record came from and when it was last checked.
- Reference
- Noisin: Unbiased Regularization for Recurrent Neural Networks
- Last updated
- 25 May 2026
What the numbers mean
About this model
Dropout-LSTM+Noise(Bernoulli) (WT2) was published by Columbia University,New York University (NYU),Princeton University, in the country recorded as United States of America, during May 2018. The category the publisher falls under is academia,Academia,Academia.
It works in the domain of Language, and is recorded as performing the task of language modeling.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
Training and provenance
Producing it required arithmetic totalling around 1.3 × 10¹⁷ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
The training set ran to roughly 2,000,000 tokens of text.
It is tracked in the underlying dataset for one reason in particular: sOTA improvement.
Answers
Dropout-LSTM+Noise(Bernoulli) (WT2) — common questions
Dropout-LSTM+Noise(Bernoulli) (WT2)— when was it released?
It was published in May 2018. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
Dropout-LSTM+Noise(Bernoulli) (WT2)— what is it used for?
It works in the domain of Language, and is recorded as handling the task of language modeling. 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.
Dropout-LSTM+Noise(Bernoulli) (WT2)— how much compute was used to train it?
Training consumed around 1.3 × 10¹⁷ 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.
Dropout-LSTM+Noise(Bernoulli) (WT2)— 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.
Dropout-LSTM+Noise(Bernoulli) (WT2)— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
Dropout-LSTM+Noise(Bernoulli) (WT2)— how many parameters does it have?
It has a parameter count of 51M. "The large network has 2 layers with 1500 hidden units each. This leads to a model complexity of 51 million 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.
Dropout-LSTM+Noise(Bernoulli) (WT2)— who created it?
It was published by Columbia University,New York University (NYU),Princeton University, based in United States of America, an organisation categorised as academia,Academia,Academia.
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.