RECONTRA-uncategorized
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
- Training data
- 57,500 tokens
- Epochs
- 100
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
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
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
- How it was established
- Operation counting
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 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
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.
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.
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.
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.
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.
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.
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.