RECONTRA-uncategorized

Closed weights 112K 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
112K

8*61*160+160*160+160*52=112000 "a network with 61 input units, 52 outputs, 160 hidden traits and 8 (4+I+3) delayed inputs" Table 1

Training data
57,500 tokens

5000*11.5=57500 The length of the non-categorized Spanish sentences ranged from 3 to 20 and the length of the non-categorized English sentences, from 3 to 17

Epochs
100

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
3.9 × 10¹² FLOP

2*112000*3*11.5*5000*100=3864000000000=3.9e12 "was trained for 100 epochs using the 5,000 pairs" "The length of the non-categorized Spanish sentences ranged from 3 to 20 and the length of the non-categorized English sentences, from 3 to 17"

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.

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

About this model

RECONTRA-uncategorized was published by its authors, in June 1999.

It works in Language, and is recorded as doing translation.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

What went into building it

The training run consumed about 3.9 × 10¹² FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

It was trained on about 57,500 tokens of text.

Its inclusion criterion is training cost.

Answers

RECONTRA-uncategorized — common questions

01

What GPU do I need to run RECONTRA-uncategorized?

None. RECONTRA-uncategorized 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 RECONTRA-uncategorized open source?

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

03

How many parameters does RECONTRA-uncategorized have?

RECONTRA-uncategorized has 112K parameters. 8*61*160+160*160+160*52=112000 "a network with 61 input units, 52 outputs, 160 hidden traits and 8 (4+I+3) delayed inputs" 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.

04

When was RECONTRA-uncategorized released?

RECONTRA-uncategorized 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.

05

What is RECONTRA-uncategorized used for?

RECONTRA-uncategorized works in Language, and is recorded as handling translation. 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.

06

How much compute was used to train RECONTRA-uncategorized?

Around 3.9 × 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.

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.