AWD-LSTM-MoS+PDR + dynamic evaluation (PTB)

Closed weights IBM 60.9M parameters August 2018

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
IBM
Organisation type
Industry
Country
United States of America
Published
14 August 2018
Authors
Siddhartha Brahma

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
60.9M

10k vocabulary "For the mixture-of-softmax model, we use a 3-layer LSTM with dimensions 960, 960 and 620, embedding dimension of 280 and 15 experts for PTB" Embedding: 10000*280=2800000 Unembedding: 10000*280*15=42000000 LSTM 1: 4*(280+960)*960=4761600 LSTM 2: 4*(960+960)*960=7372800 LSTM 3: 4*(960+620)*620=3918400 Total: 2800000+42000000+4761600+7372800+3918400=60852800

Training data
929,000 tokens
Epochs
1,200

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
4.1 × 10¹⁷ FLOP

Forward flop: 2*60852800=121705600 FLOP: 1200*121705600*3*929000=4.0703221e+17

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.

Record confidence
Likely
Benchmark data
AWD-LSTM-MoS+PDR + dynamic evaluation (PTB)

Sources

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

Reference
Improved Language Modeling by Decoding the Past
Last updated
11 February 2026

What the numbers mean

Where it came from

AWD-LSTM-MoS+PDR + dynamic evaluation (PTB) was published by IBM, in United States of America, in August 2018. industry is the category the publisher falls under.

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.

Training and provenance

The training run consumed about 4.1 × 10¹⁷ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

The training set ran to roughly 929,000 tokens.

Answers

AWD-LSTM-MoS+PDR + dynamic evaluation (PTB) — common questions

01

Who created AWD-LSTM-MoS+PDR + dynamic evaluation (PTB)?

AWD-LSTM-MoS+PDR + dynamic evaluation (PTB) was published by IBM, based in United States of America, categorised as industry.

02

When was AWD-LSTM-MoS+PDR + dynamic evaluation (PTB) released?

AWD-LSTM-MoS+PDR + dynamic evaluation (PTB) was published in August 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.

03

What is AWD-LSTM-MoS+PDR + dynamic evaluation (PTB) used for?

AWD-LSTM-MoS+PDR + dynamic evaluation (PTB) 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.

04

How much compute was used to train AWD-LSTM-MoS+PDR + dynamic evaluation (PTB)?

Around 4.1 × 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.

05

What GPU do I need to run AWD-LSTM-MoS+PDR + dynamic evaluation (PTB)?

None. AWD-LSTM-MoS+PDR + dynamic evaluation (PTB) 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.

06

Is AWD-LSTM-MoS+PDR + dynamic evaluation (PTB) open source?

No. AWD-LSTM-MoS+PDR + dynamic evaluation (PTB) has not had its weights published, so it exists only as a service controlled by its owner.

07

How many parameters does AWD-LSTM-MoS+PDR + dynamic evaluation (PTB) have?

AWD-LSTM-MoS+PDR + dynamic evaluation (PTB) has 60.9M parameters. 10k vocabulary "For the mixture-of-softmax model, we use a 3-layer LSTM with dimensions 960, 960 and 620, embedding dimension of 280 and 15 experts for PTB" Embedding: 10000*280=2800000 Unembedding: 10000*280*15=42000000 LSTM 1: 4*(280+960)*960=4761600 LSTM 2: 4*(960+960)*960=7372800 LSTM 3: 4*(960+620)*620=3918400 Total: 2800000+42000000+4761600+7372800+3918400=60852800. 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.

Source

Original publication

Record last updated 11 February 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.