AWD-LSTM - 3-layer LSTM (tied) + continuous cache pointer (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
- Salesforce Research
- Organisation type
- Industry
- Country
- United States of America
- Published
- 7 August 2017
- Authors
- Stephen Merity, Nitish Shirish Keskar, Richard Socher
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
- 33M
- Training data
- 2,000,000 tokens
- Epochs
- 750
33M (Table 2)
"For training the models, we use the NT-ASGD algorithm discussed in the previous section for 750 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
- 3 × 10¹⁷ FLOP
- How it was established
- Operation counting
6 FLOP / parameter / token * 33000000 parameters * 2000000 tokens * 750 epochs = 2.97e+17 FLOP
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
- Open source
bsd-3 license: https://github.com/salesforce/awd-lstm-lm train/eval code: https://github.com/salesforce/awd-lstm-lm/blob/master/main.py
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,SOTA improvement
- Record confidence
- Confident
- Citations
- 1,176
- Benchmark data
- AWD-LSTM - 3-layer LSTM (tied) + continuous cache pointer (WT2)
"we achieve an even lower state-of-the-art perplexity of 52.8 on Penn Treebank and 52.0 on WikiText-2."
Sources
Where this record came from and when it was last checked.
- Reference
- Regularizing and Optimizing LSTM Language Models
- Last updated
- 11 February 2026
What the numbers mean
Background
AWD-LSTM - 3-layer LSTM (tied) + continuous cache pointer (WT2) was published by Salesforce Research, in the country recorded as United States of America, during August 2017. 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
Producing it required arithmetic totalling around 3 × 10¹⁷ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
It was trained on a corpus of about 2,000,000 tokens of text.
It is tracked in the underlying dataset for one reason in particular: highly cited,SOTA improvement.
Answers
AWD-LSTM - 3-layer LSTM (tied) + continuous cache pointer (WT2) — common questions
AWD-LSTM - 3-layer LSTM (tied) + continuous cache pointer (WT2)— when was it released?
It was published in August 2017. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
AWD-LSTM - 3-layer LSTM (tied) + continuous cache pointer (WT2)— what is it used for?
It works in the domain of Language, and is recorded as handling the task of language modeling. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
AWD-LSTM - 3-layer LSTM (tied) + continuous cache pointer (WT2)— how much compute was used to train it?
Training consumed around 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.
AWD-LSTM - 3-layer LSTM (tied) + continuous cache pointer (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.
AWD-LSTM - 3-layer LSTM (tied) + continuous cache pointer (WT2)— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
AWD-LSTM - 3-layer LSTM (tied) + continuous cache pointer (WT2)— how many parameters does it have?
It has a parameter count of 33M. 33M (Table 2). 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.
AWD-LSTM - 3-layer LSTM (tied) + continuous cache pointer (WT2)— who created it?
It was published by Salesforce Research, based in United States of America, an organisation categorised as industry.
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.