genCNN + dyn eval
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
- Chinese Academy of Sciences,Huawei Noah's Ark Lab,Dublin City University
- Organisation type
- Academia,Industry,Academia
- Country
- China, Ireland
- Published
- 17 March 2015
- Authors
- Mingxuan Wang, Zhengdong Lu, Hang Li, Wenbin Jiang, Qun Liu
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
- 8M
- Training data
- 929,000 tokens
8M according to https://arxiv.org/pdf/1508.06615
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
- 3.4 × 10¹⁶ FLOP
- How it was established
- Hardware,Operation counting
5046000000000 FLOP / sec/ GPU * 1 GPU * 48 hours ["Likely" confidence since 2 days of training refer to another dataset] * 3600 sec / hour * 0.3 [assumed utilization] = 2.6158464e+17 FLOP Assuming (!) 100 epochs (-> "Speculative" confidence"): 6 FLOP / parameter / token * 8000000 parameters * 929000 tokens * 100 epochs = 4.4592e+15 FLOP sqrt(2.6158464e+17*4.4592e+15 ) = 3.4153451e+16 FLOP ________ in the algorithmic progress report paper the estimation was 7.3 × 10^16 FLOP (hardware-based es…
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 Tesla K40s
- Wall-clock time
- 48 hours
" The optimization is done mainly on a Tesla K40 GPU, which takes about 2 days for the training on a dataset containing 1M sentences." this training doesn't refer to the PTB dataset but to wiki dataset so it is likely an upper bound
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
- Record confidence
- Speculative
- Citations
- 33
- Benchmark data
- genCNN + dyn eval
"genCNN outperforms the state-ofthe-arts with big margins."
Sources
Where this record came from and when it was last checked.
- Reference
- genCNN: A Convolutional Architecture for Word Sequence Prediction
- Last updated
- 28 November 2025
What the numbers mean
Background
genCNN + dyn eval was published by Chinese Academy of Sciences,Huawei Noah's Ark Lab,Dublin City University, in the country recorded as China, during March 2015. The category the publisher falls under is academia,Industry,Academia.
It works in the domain of Language, and is recorded as performing the task of 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
Training it took a computation budget of roughly 3.4 × 10¹⁶ FLOP, on hardware recorded as NVIDIA Tesla K40s. 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 929,000 tokens of text.
It is tracked in the underlying dataset for one reason in particular: sOTA improvement.
Answers
genCNN + dyn eval — common questions
genCNN + dyn eval— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
genCNN + dyn eval— how many parameters does it have?
It has a parameter count of 8M. 8M according to https://arxiv.org/pdf/1508.06615. 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.
genCNN + dyn eval— who created it?
It was published by Chinese Academy of Sciences,Huawei Noah's Ark Lab,Dublin City University, based in China, an organisation categorised as academia,Industry,Academia.
genCNN + dyn eval— when was it released?
It was published in March 2015. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
genCNN + dyn eval— what is it used for?
It works in the domain of Language, and is recorded as handling the task of language modeling. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
genCNN + dyn eval— how much compute was used to train it?
Training consumed around 3.4 × 10¹⁶ FLOP, on hardware recorded as NVIDIA Tesla K40s. 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.
genCNN + dyn eval— 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.