LSTM + dynamic eval

Closed weights University of Edinburgh 50M parameters September 2017

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
University of Edinburgh
Organisation type
Academia
Country
United Kingdom of Great Britain and Northern Ireland
Published
21 September 2017
Authors
Ben Krause, Emmanuel Kahembwe, Iain Murray, Steve Renals

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
50M

table 2

Training data
90,000,000 tokens

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-2: https://github.com/benkrause/dynamic-evaluation

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

"Dynamic evaluation outperforms existing adaptation approaches in our comparisons. Dynamic evaluation improves the state-of-the-art word-level perplexities on the Penn Treebank and WikiText-2 datasets to 51.1 and 44.3 respectively"

Record confidence
Likely
Citations
147
Benchmark data
LSTM + dynamic eval

Sources

Where this record came from and when it was last checked.

Reference
Dynamic Evaluation of Neural Sequence Models
Last updated
25 May 2026

What the numbers mean

Background

LSTM + dynamic eval was published by University of Edinburgh, in United Kingdom of Great Britain and Northern Ireland, in September 2017. It comes out of academia.

It works in Language, and is recorded as doing language modeling.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

What went into building it

Around 90,000,000 tokens went into training it.

It is tracked in the underlying dataset for one reason in particular: sOTA improvement.

Answers

LSTM + dynamic eval — common questions

01

Is LSTM + dynamic eval open source?

No. LSTM + dynamic eval has not had its weights published, so it exists only as a service controlled by its owner.

02

How many parameters does LSTM + dynamic eval have?

LSTM + dynamic eval has 50M parameters. 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.

03

Who created LSTM + dynamic eval?

LSTM + dynamic eval was published by University of Edinburgh, based in United Kingdom of Great Britain and Northern Ireland, categorised as academia.

04

When was LSTM + dynamic eval released?

LSTM + dynamic eval was published in September 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.

05

What is LSTM + dynamic eval used for?

LSTM + dynamic eval works in Language, and is recorded as handling language modeling. These are the areas it was designed around; they describe intent rather than a hard boundary.

06

What GPU do I need to run LSTM + dynamic eval?

None. LSTM + dynamic eval 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.

Source

Original publication

Record last updated 25 May 2026

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.