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 Israel, in October 2018. It comes out of academia,Industry.
It works in Language, and is recorded as doing 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 around 3.2 × 10¹⁷ FLOP of arithmetic, on NVIDIA Tesla K80, which is a statement about the training budget rather than about inference.
Around 14,162,842 tokens went into training it.
Answers
code2vec — common questions
What is code2vec used for?
code2vec 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.
Where can I download code2vec?
The weights for code2vec are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
How much compute was used to train code2vec?
Around 3.2 × 10¹⁷ FLOP, on 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.
What GPU do I need to run code2vec?
We cannot say. code2vec 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.
Is code2vec open source?
Its weights are published, so code2vec 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.
How many parameters does code2vec have?
No parameter count has been published for code2vec, which is why no memory or speed figure appears on this page.
Who created code2vec?
code2vec was published by Technion - Israel Institute of Technology,Facebook AI Research, based in Israel, categorised as academia,Industry.
When was code2vec released?
code2vec 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.