VDCNN (on Amazon Review Full dataset)

Closed weights Facebook AI Research,University of Le Mans 7.8M parameters January 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
Facebook AI Research,University of Le Mans
Organisation type
Industry,Academia
Country
United States of America, France
Published
27 January 2017
Authors
Alexis Conneau, Holger Schwenk, Loïc Barrault, Yann Lecun

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Language
Task
Text classification

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
7.8M

7.8 M from Table 2.

Training data
tokens

Table 3: Amazon Review Full 3 000k

Epochs
15
Batch size
128

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
5.7 × 10¹⁷ FLOP

5050000000000 [peak FLOPs] * 15 [epochs] * 7 [h] * 3600 [s] * 0.3 [assumed utilization rate] = 5.7267e+17

How it was established
Hardware

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware
NVIDIA Tesla K40s
Chips used
1
Power draw
282 W

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Confident

Sources

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

Reference
Very Deep Convolutional Networks for Text Classification
Last updated
11 February 2026

What the numbers mean

Background

VDCNN (on Amazon Review Full dataset) was published by Facebook AI Research,University of Le Mans, in United States of America, in January 2017. The organisation is categorised as industry,Academia.

It works in Language, and is recorded as doing text classification.

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 5.7 × 10¹⁷ FLOP, on NVIDIA Tesla K40s. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

Answers

VDCNN (on Amazon Review Full dataset) — common questions

01

When was VDCNN (on Amazon Review Full dataset) released?

VDCNN (on Amazon Review Full dataset) was published in January 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.

02

What is VDCNN (on Amazon Review Full dataset) used for?

VDCNN (on Amazon Review Full dataset) works in Language, and is recorded as handling text classification. 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.

03

How much compute was used to train VDCNN (on Amazon Review Full dataset)?

Around 5.7 × 10¹⁷ FLOP, on NVIDIA Tesla K40s. 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.

04

What GPU do I need to run VDCNN (on Amazon Review Full dataset)?

None. VDCNN (on Amazon Review Full dataset) 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.

05

Is VDCNN (on Amazon Review Full dataset) open source?

The licensing for VDCNN (on Amazon Review Full dataset) was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

06

How many parameters does VDCNN (on Amazon Review Full dataset) have?

VDCNN (on Amazon Review Full dataset) has 7.8M parameters. 7.8 M from 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.

07

Who created VDCNN (on Amazon Review Full dataset)?

VDCNN (on Amazon Review Full dataset) was published by Facebook AI Research,University of Le Mans, based in United States of America, categorised as industry,Academia.

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.