GCRN-M1, dropout

Closed weights Ecole Polytechnique F´ed´erale de Lausanne (EPFL) 42M parameters December 2016

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
Ecole Polytechnique F´ed´erale de Lausanne (EPFL)
Organisation type
Academia
Country
Switzerland
Published
22 December 2016
Authors
Youngjoo Seo, Michaël Defferrard, Pierre Vandergheynst, Xavier Bresson

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
42M

42M (Table 2)

Training data
929,000 tokens

"All experiments have 13 epochs"

Epochs
13

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 × 10¹⁵ FLOP

6 FLOP / parameter / token * 42000000 parameters * 929000 tokens * 13 epochs = 3.043404e+15 FLOP

How it was established
Operation counting

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
Confident
Citations
957
Benchmark data
GCRN-M1, dropout

Sources

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

Reference
Structured Sequence Modeling with Graph Convolutional Recurrent Networks
Last updated
25 May 2026

What the numbers mean

Where it came from

GCRN-M1, dropout was published by Ecole Polytechnique F´ed´erale de Lausanne (EPFL), in Switzerland, in December 2016. academia 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.

What went into building it

The training run consumed about 3 × 10¹⁵ 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

GCRN-M1, dropout — common questions

01

What GPU do I need to run GCRN-M1, dropout?

None. GCRN-M1, dropout 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.

02

Is GCRN-M1, dropout open source?

No. GCRN-M1, dropout has not had its weights published, so it exists only as a service controlled by its owner.

03

How many parameters does GCRN-M1, dropout have?

GCRN-M1, dropout has 42M parameters. 42M (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.

04

Who created GCRN-M1, dropout?

GCRN-M1, dropout was published by Ecole Polytechnique F´ed´erale de Lausanne (EPFL), based in Switzerland, categorised as academia.

05

When was GCRN-M1, dropout released?

GCRN-M1, dropout was published in December 2016. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

06

What is GCRN-M1, dropout used for?

GCRN-M1, dropout 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.

07

How much compute was used to train GCRN-M1, dropout?

Around 3 × 10¹⁵ 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.

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.