code2vec
No estimate
No hardware requirements for this model
This model's weights are open, but no parameter count has been published for it. Every memory and speed figure starts from that number, so we would rather show nothing than a fabricated estimate.
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
- Technion - Israel Institute of Technology,Facebook AI Research
- Organisation type
- Academia,Industry
- Country
- Israel, United States of America, France
- Published
- 30 October 2018
- Authors
- Uri Alon, Meital Zilberstein, Omer Levy, Eran Yahav
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.
- Training data
- 14,162,842 tokens
- Epochs
- 12
We used a data set of 10, 072 Java GitHub repositories, originally introduced by Alon et al. [2018]. In this dataset, the files from all the projects are shuffled and split to 14,162,842 training (66GB), 415, 046 validation and 413, 915 of test methods "the average method length is 7 lines" [of code]
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
- 3.2 × 10¹⁷ FLOP
- How it was established
- Hardware
8126000000000.000 * 36 * 3600 * 0.3 = 3.1593888e+17
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 K80
- Wall-clock time
- 36 hours
When training on a single Tesla K80 GPU, we achieve a training throughput of more than 1000 methods per second. Therefore, a single training epoch takes about 3 hours, and it takes about 1.5 days to completely train a model. 36/3 = 12 epochs
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
- Open — downloadable
- Model access
- Open weights (unrestricted)
- Training code
- Open source
MIT License https://github.com/tech-srl/code2vec
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- code2vec: Learning Distributed Representations of Code
- Last updated
- 28 November 2025
What the numbers mean
What this model is
code2vec was published by Technion - Israel Institute of Technology,Facebook AI Research, in the country recorded as Israel, during October 2018. It comes out of an organisation categorised as academia,Industry.
It works in the domain of Language, and is recorded as performing the task of language modeling.
Published weights mean the model runs on your machine rather than someone else's, which is what makes the hardware question below answerable at all.
How it was trained
Producing it required arithmetic totalling around 3.2 × 10¹⁷ FLOP, on hardware recorded as NVIDIA Tesla K80. That figure measures what producing the model cost, and has no bearing on how fast it answers.
Training consumed a corpus of around 14,162,842 tokens of text.
Answers
code2vec — common questions
code2vec— what is it used for?
It works in the domain of Language, and is recorded as handling the task of 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.
code2vec— where can I download it?
The weights are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
code2vec— how much compute was used to train it?
Training consumed around 3.2 × 10¹⁷ FLOP, on hardware recorded as NVIDIA Tesla K80. 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.
code2vec— what GPU do I need to run it?
We cannot say. It has open weights, but no parameter count has been published for it, and every memory and speed calculation starts from that number. We would rather show nothing than a fabricated estimate.
code2vec— is it open source?
Its weights are published, so it can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.
code2vec— how many parameters does it have?
No parameter count has been published for it, which is why no memory or speed figure appears on this page.
code2vec— who created it?
It was published by Technion - Israel Institute of Technology,Facebook AI Research, based in Israel, an organisation categorised as academia,Industry.
code2vec— when was it released?
It was published in October 2018. 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.