CT-MoS (WT2)

Closed weights Google,National Tsing Hua University 45M parameters December 2020

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
Google,National Tsing Hua University
Organisation type
Industry,Academia
Country
United States of America, Taiwan
Published
25 December 2020
Authors
Pei-Hsin Wang, Sheng-Iou Hsieh, Shih-Chieh Chang, Yu-Ting Chen, Jia-Yu Pan, Wei Wei, Da-Chang Juan

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
45M

45M Table 2

Training data
2,000,000 tokens
Epochs
1,000

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
5.4 × 10¹⁷ FLOP

6 FLOP / parameter / token * 45000000 parameters * 2000000 tokens * 1000 epochs = 5.4e+17 FLOP

How it was established
Operation counting

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 1080 Ti
Chips used
4
Power draw
2.0 kW

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
Unreleased

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

"Experimental results confirm that the proposed method significantly improves state-of-the-art language models, achieving a perplexity of 55.31 and 62.89 on the test set of Penn Treebank and WikiText-2"

Record confidence
Confident
Citations
36
Benchmark data
CT-MoS (WT2)

Sources

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

Reference
Contextual Temperature for Language Modeling
Last updated
25 May 2026

What the numbers mean

What this model is

CT-MoS (WT2) was published by Google,National Tsing Hua University, in United States of America, in December 2020. industry,Academia is the category the publisher falls under.

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

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

How it was trained

Producing it required around 5.4 × 10¹⁷ FLOP of arithmetic, on NVIDIA GeForce GTX 1080 Ti, which is a statement about the training budget rather than about inference.

The training set ran to roughly 2,000,000 tokens.

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

Answers

CT-MoS (WT2) — common questions

01

How many parameters does CT-MoS (WT2) have?

CT-MoS (WT2) has 45M parameters. 45M 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.

02

Who created CT-MoS (WT2)?

CT-MoS (WT2) was published by Google,National Tsing Hua University, based in United States of America, categorised as industry,Academia.

03

When was CT-MoS (WT2) released?

CT-MoS (WT2) was published in December 2020. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

04

What is CT-MoS (WT2) used for?

CT-MoS (WT2) works in Language, and is recorded as handling language modeling. 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.

05

How much compute was used to train CT-MoS (WT2)?

Around 5.4 × 10¹⁷ FLOP, on NVIDIA GeForce GTX 1080 Ti. 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.

06

What GPU do I need to run CT-MoS (WT2)?

None. CT-MoS (WT2) 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.

07

Is CT-MoS (WT2) open source?

No. CT-MoS (WT2) has not had its weights published, so it exists only as a service controlled by its owner.

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.