Transformer-C
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
- University of Massachusetts Amherst
- Organisation type
- Academia
- Country
- United States of America
- Published
- 8 April 2021
- Authors
- Simeng Sun, Mohit Iyyer
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
- 148M
- Training data
- 103,000,000 tokens
- Epochs
- 19.88
- Batch size
- 10,240
148M, Table 6
Table 7 steps 200k batch size 10240 10240 * 200000 / 103000000 = 19.88 epochs
table 7
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
- 1.9 × 10¹⁸ FLOP
- How it was established
- Operation counting,Hardware
6 FLOP / token / parameter * 148000000 parameters * 10240 tokens per batch * 200000 steps = 1.818624e+18 FLOP 11340000000000 FLOP / sec [assumed fp32] * 4 GPUs * 40 hours * 3600 sec/ hour * 0.3 [assumed precision] = 1.959552e+18 FLOP geometric mean: sqrt(1.818624e+18*1.959552e+18) = 1.8877734e+18
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
- Wall-clock time
- 40 hours
- Power draw
- 2.0 kW
table 7
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
permissive license, BSD-3: https://github.com/SimengSun/revisit-nplm
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Confident
- Citations
- 16
- Benchmark data
- Transformer-C
Sources
Where this record came from and when it was last checked.
- Reference
- Revisiting Simple Neural Probabilistic Language Models
- Last updated
- 25 May 2026
What the numbers mean
Where it came from
Transformer-C was published by University of Massachusetts Amherst, in United States of America, in April 2021. It comes out of academia.
It works in Language, and is recorded as doing language modeling.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
How it was trained
Training it took roughly 1.9 × 10¹⁸ FLOP of computation, on NVIDIA GeForce GTX 1080 Ti — a measure of what producing the model cost, not of how fast it answers.
The training set ran to roughly 103,000,000 tokens.
Answers
Transformer-C — common questions
What is Transformer-C used for?
Transformer-C 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.
How much compute was used to train Transformer-C?
Around 1.9 × 10¹⁸ 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.
What GPU do I need to run Transformer-C?
None. Transformer-C 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.
Is Transformer-C open source?
No. Transformer-C has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does Transformer-C have?
Transformer-C has 148M parameters. 148M, Table 6. 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.
Who created Transformer-C?
Transformer-C was published by University of Massachusetts Amherst, based in United States of America, categorised as academia.
When was Transformer-C released?
Transformer-C was published in April 2021. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
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.