Named Entity Recognition model

Closed weights Carnegie Mellon University (CMU) March 2016

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
Carnegie Mellon University (CMU)
Organisation type
Academia
Country
United States of America
Published
4 March 2016
Authors
Xuezhe Ma, Eduard Hovy

What it does

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

Domain
Language
Task
Named entity recognition (NER), Language modeling
Numerical format
FP32

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.

Training data
204,567 tokens

Table 2. 204567 tokens

Epochs
50

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
9.7 × 10¹⁶ FLOP

8 hours of training for NER GeForce GTX TITAN X GPU 0.33 utilization rate

How it was established
Hardware

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware
NVIDIA GeForce GTX TITAN X
Chips used
1
Chip-hours
8
Wall-clock time
8 hours

"the model training requires about 12 hours for POS tagging and 8 hours for NER"

Power draw
290 W

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
Discretionary
Record confidence
Confident
Citations
3,100

Sources

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

Reference
End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
Last updated
28 November 2025

What the numbers mean

About this model

Named Entity Recognition model was published by Carnegie Mellon University (CMU), in the country recorded as United States of America, during March 2016. The publishing organisation is categorised as academia.

It works in the domain of Language, and is recorded as performing the task of named entity recognition (NER), Language modeling.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

Training and provenance

The training run consumed about 9.7 × 10¹⁶ FLOP, on hardware recorded as NVIDIA GeForce GTX TITAN X. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Training consumed a corpus of around 204,567 tokens of text.

It is tracked in the underlying dataset for one reason in particular: discretionary.

Answers

Named Entity Recognition model — common questions

01

Named Entity Recognition model— when was it released?

It was published in March 2016. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

02

Named Entity Recognition model— what is it used for?

It works in the domain of Language, and is recorded as handling the task of named entity recognition (NER), Language modeling. These are the areas it was designed around; they describe intent rather than a hard boundary.

03

Named Entity Recognition model— how much compute was used to train it?

Training consumed around 9.7 × 10¹⁶ FLOP, on hardware recorded as NVIDIA GeForce GTX TITAN X. 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.

04

Named Entity Recognition model— 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.

05

Named Entity Recognition model— 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.

06

Named Entity Recognition model— how many parameters does it have?

No parameter count has been published for it, which is why no memory or speed figure appears on this page.

07

Named Entity Recognition model— who created it?

It was published by Carnegie Mellon University (CMU), based in United States of America, an organisation categorised as academia.

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.