Transformer-XL Large + Phrase Induction
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
- Massachusetts Institute of Technology (MIT),University of Illinois Urbana-Champaign (UIUC)
- Organisation type
- Academia,Academia
- Country
- United States of America
- Published
- 4 June 2019
- Authors
- Hongyin Luo, Lan Jiang, Yonatan Belinkov, James Glass
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Language modeling/generation
- Base model
- Transformer-XL (257M)
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
- 257M
- Training data
- 103,000,000 tokens
- Epochs
- 1
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
- 3.8 × 10²⁰ FLOP
- How it was established
- Operation counting
- Fine-tuning compute
- 1.6 × 10¹⁷ FLOP
Fine-tuned from pre-trained Transformer-XL Large (upd 3.7832771e+20 FLOP, old estimation 1.09e19 FLOP). Total: 3.7832771e20 + 1.588e17 = 3.7848651e+20 FLOP (Speculative confidence same as Transformer XL)
Additional 1.6e17 FLOP of fine-tuning from one epoch on WikiText-103: 6 * 257M * 103M = 1.588e17 FLOP.
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
code license, BSD-3: https://github.com/luohongyin/PILM?tab=BSD-3-Clause-1-ov-file#readme training: https://github.com/luohongyin/PILM/blob/master/train_span_wt103.sh
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
- Record confidence
- Speculative
- Citations
- 14
- Benchmark data
- Transformer-XL Large + Phrase Induction
"We achieved a new state-of-the-art performance of 17.4 perplexity on the Wikitext-103 dataset"
Sources
Where this record came from and when it was last checked.
- Reference
- Improving Neural Language Models by Segmenting, Attending, and Predicting the Future
- Last updated
- 1 December 2025
What the numbers mean
What this model is
Transformer-XL Large + Phrase Induction was published by Massachusetts Institute of Technology (MIT),University of Illinois Urbana-Champaign (UIUC), in the country recorded as United States of America, during June 2019. The publishing organisation is categorised as academia,Academia.
It works in the domain of Language, and is recorded as performing the task of language modeling/generation.
It builds on Transformer-XL (257M). That is why it shares the base model's general shape and size.
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 3.8 × 10²⁰ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
It was trained on a corpus of about 103,000,000 tokens of text.
Its inclusion criterion: sOTA improvement.
Answers
Transformer-XL Large + Phrase Induction — common questions
Transformer-XL Large + Phrase Induction— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
Transformer-XL Large + Phrase Induction— how many parameters does it have?
It has a parameter count of 257M. 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.
Transformer-XL Large + Phrase Induction— who created it?
It was published by Massachusetts Institute of Technology (MIT),University of Illinois Urbana-Champaign (UIUC), based in United States of America, an organisation categorised as academia,Academia.
Transformer-XL Large + Phrase Induction— when was it released?
It was published in June 2019. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
Transformer-XL Large + Phrase Induction— what is it used for?
It works in the domain of Language, and is recorded as handling the task of language modeling/generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
Transformer-XL Large + Phrase Induction— how much compute was used to train it?
Training consumed around 3.8 × 10²⁰ 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.
Transformer-XL Large + Phrase Induction— 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.
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.