DrLIM

Closed weights New York University (NYU) 37.1K parameters June 2006

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
New York University (NYU)
Organisation type
Academia
Country
United States of America
Published
17 June 2006
Authors
R. Hadsell; S. Chopra; Y. LeCun

What it does

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

Domain
Other
Task
Image embedding

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
37.1K

Architecture described in figure 3

Training data
36,060,000 tokens

"The dataset was split into 660 training images and a 312 test images. The result of training on all 10989 similar pairs and 206481 dissimilar pairs is a 3-dimensional manifold in the shape of a cylinder (see figure 8)." 206481 + 10989 = 217470

How it is classified

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

Citations
4,888

Sources

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

Reference
Dimensionality Reduction by Learning an Invariant Mapping
Last updated
28 November 2025

What the numbers mean

Background

DrLIM was published by New York University (NYU), in United States of America, in June 2006. The organisation is categorised as academia.

It works in Other, and is recorded as doing image embedding.

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

Training and provenance

Around 36,060,000 tokens went into training it.

Answers

DrLIM — common questions

01

What GPU do I need to run DrLIM?

None. DrLIM 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 DrLIM open source?

The licensing for DrLIM 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 DrLIM have?

DrLIM has 37.1K parameters. Architecture described in figure 3. 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

Who created DrLIM?

DrLIM was published by New York University (NYU), based in United States of America, categorised as academia.

05

When was DrLIM released?

DrLIM was published in June 2006. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

06

What is DrLIM used for?

DrLIM works in Other, and is recorded as handling image embedding. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

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.