LIRA
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
- Instituto de Ciencias Aplicadas y Technologia
- Organisation type
- Academia
- Country
- Mexico
- Published
- 30 July 2004
- Authors
- E Kussul, T Baidyk
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Character recognition (OCR)
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
- 100K
- Training data
- 1,020,000 tokens
"For the first modification of the Rosenblatt perceptron 10 neurons were included into the R-layer. [...] The number of the A-layer neurons was 256,000" The relation between the S-layer and A-layer is hardcoded
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Citations
- 188
Sources
Where this record came from and when it was last checked.
- Reference
- Improved method of handwritten digit recognition tested on MNIST database
- Last updated
- 28 November 2025
What the numbers mean
What this model is
LIRA was published by Instituto de Ciencias Aplicadas y Technologia, in the country recorded as Mexico, during July 2004. The category the publisher falls under is academia.
It works in the domain of Vision, and is recorded as performing the task of character recognition (OCR).
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
Training and provenance
Training consumed a corpus of around 1,020,000 tokens of text.
Answers
LIRA — common questions
LIRA— 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.
LIRA— how many parameters does it have?
It has a parameter count of 100K. "For the first modification of the Rosenblatt perceptron 10 neurons were included into the R-layer. [...] The number of the A-layer neurons was 256,000" The relation between the S-layer and A-layer is hardcoded. 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.
LIRA— who created it?
It was published by Instituto de Ciencias Aplicadas y Technologia, based in Mexico, an organisation categorised as academia.
LIRA— when was it released?
It was published in July 2004. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
LIRA— what is it used for?
It works in the domain of Vision, and is recorded as handling the task of character recognition (OCR). Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
LIRA— 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.
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.