TrellisNet

Closed weights Carnegie Mellon University (CMU),Bosch Center for Artificial Intelligence,Intel Labs 180M parameters October 2018

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),Bosch Center for Artificial Intelligence,Intel Labs
Organisation type
Academia,Industry,Industry
Country
United States of America, Germany
Published
15 October 2018
Authors
Shaojie Bai, J. Zico Kolter, Vladlen Koltun

What it does

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

Domain
Language
Task
Language modeling

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
180M

180M, Table 2

Training data
103,000,000 tokens
Epochs
25

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
2.8 × 10¹⁸ FLOP

6 FLOP / parameter / token * 180000000 parameters * 103000000 tokens * 25 epochs = 2.781e+18 FLOP

How it was established
Operation counting

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
Unreleased
Training code
Open source

MIT license for code: https://github.com/locuslab/trellisnet/tree/master/TrellisNet/word_WT103

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
SOTA improvement

"Experiments demonstrate that trellis networks outperform the current state of the art methods on a variety of challenging benchmarks, including word-level language modeling and character-level language modeling tasks" "On word-level WikiText-103, a trellis network outperforms by 7.6% in perplexity the contemporaneous self-attention-based Relational Memory Core (Santoro et al., 2018), and by 11.5% the work of Merity et al. (2018a). (Concurrently with our work, Dai et al. (2019) employ a transfo…

Record confidence
Confident
Citations
164
Benchmark data
TrellisNet

Sources

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

Reference
Trellis Networks for Sequence Modeling
Last updated
25 May 2026

What the numbers mean

What this model is

TrellisNet was published by Carnegie Mellon University (CMU),Bosch Center for Artificial Intelligence,Intel Labs, in United States of America, in October 2018. The organisation is categorised as academia,Industry,Industry.

It works in Language, and is recorded as doing language modeling.

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

How it was trained

Producing it required around 2.8 × 10¹⁸ FLOP of arithmetic, which is a statement about the training budget rather than about inference.

It was trained on about 103,000,000 tokens of text.

The reason it appears in this catalogue at all is sOTA improvement.

Answers

TrellisNet — common questions

01

Who created TrellisNet?

TrellisNet was published by Carnegie Mellon University (CMU),Bosch Center for Artificial Intelligence,Intel Labs, based in United States of America, categorised as academia,Industry,Industry.

02

When was TrellisNet released?

TrellisNet was published in October 2018. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

03

What is TrellisNet used for?

TrellisNet works in Language, and is recorded as handling language modeling. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

04

How much compute was used to train TrellisNet?

Around 2.8 × 10¹⁸ 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.

05

What GPU do I need to run TrellisNet?

None. TrellisNet 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.

06

Is TrellisNet open source?

No. TrellisNet has not had its weights published, so it exists only as a service controlled by its owner.

07

How many parameters does TrellisNet have?

TrellisNet has 180M parameters. 180M, Table 2. 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.

Source

Original publication

Record last updated 25 May 2026

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.