TCAN (WT2)

Closed weights Nanjing University,Ant Group 33M parameters February 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
Nanjing University,Ant Group
Organisation type
Academia,Industry
Country
China
Published
28 February 2020
Authors
Hongyan Hao, Yan Wang, Yudi Xia, Jian Zhao, Furao Shen

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
33M
Training data
2,000,000 tokens

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/haohy/TCAN

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

"We improve the state-of-theart results of ... 9.20 on WikiText-2"

Record confidence
Confident
Citations
47
Benchmark data
Temporal Convolutional Attention-based Network(TCAN) (WT2)

Sources

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

Reference
Temporal Convolutional Attention-based Network For Sequence Modeling
Last updated
11 February 2026

What the numbers mean

About this model

TCAN (WT2) was published by Nanjing University,Ant Group, in China, in February 2020. The organisation is categorised as academia,Industry.

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.

Training and provenance

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

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

Answers

TCAN (WT2) — common questions

01

What GPU do I need to run TCAN (WT2)?

None. TCAN (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.

02

Is TCAN (WT2) open source?

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

03

How many parameters does TCAN (WT2) have?

TCAN (WT2) has 33M parameters. 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 TCAN (WT2)?

TCAN (WT2) was published by Nanjing University,Ant Group, based in China, categorised as academia,Industry.

05

When was TCAN (WT2) released?

TCAN (WT2) was published in February 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.

06

What is TCAN (WT2) used for?

TCAN (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.

Source

Original publication

Record last updated 11 February 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.