RECONTRA-categorized

Closed weights 66.8K parameters June 1999

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.

Published
2 June 1999
Authors
M. A. Castaño, F. Casacuberta

What it does

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

Domain
Language
Task
Translation
Approach
Supervised

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
66.8K

6*50*140+140*140+140*37=66780 Table 1

Training data
40,000 tokens

5000*8=40000 words The number of words of the categorized sentences ranged from 3 to 13 for the Spanish ones and from 3 to 12 for the English ones.

Epochs
500

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
8 × 10¹² FLOP

2*66780*3*500*5000*8=8013600000000=8e12 "The number of words of the categorized sentences ranged from 3 to 13 for the Spanish ones and from 3 to 12 for the English ones." "was trained up to 500 epochs using the 5,000 categorized pairs"

How it was established
Operation counting

How it is classified

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

Frontier model
Yes
Why it is tracked
Training cost
Record confidence
Likely

Sources

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

Reference
Text-to-text machine translation using the RECONTRA connectionist model
Last updated
28 November 2025

What the numbers mean

What this model is

RECONTRA-categorized was published by its authors, during June 1999.

It works in the domain of Language, and is recorded as performing the task of translation.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

What went into building it

Producing it required arithmetic totalling around 8 × 10¹² FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Training consumed a corpus of around 40,000 tokens of text.

Its inclusion criterion: training cost.

Answers

RECONTRA-categorized — common questions

01

RECONTRA-categorized— how many parameters does it have?

It has a parameter count of 66.8K. 6*50*140+140*140+140*37=66780 Table 1. 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.

02

RECONTRA-categorized— when was it released?

It was published in June 1999. 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

RECONTRA-categorized— what is it used for?

It works in the domain of Language, and is recorded as handling the task of translation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

04

RECONTRA-categorized— how much compute was used to train it?

Training consumed around 8 × 10¹² 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

RECONTRA-categorized— 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.

06

RECONTRA-categorized— is it open source?

The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

Source

Original publication

Record last updated 28 November 2025

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.