CPC v2
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
- DeepMind,University of California (UC) Berkeley
- Organisation type
- Industry,Academia
- Country
- United Kingdom of Great Britain and Northern Ireland, United States of America
- Published
- 22 May 2019
- Authors
- Olivier J. Hénaff, Aravind Srinivas, Jeffrey De Fauw, Ali Razavi, Carl Doersch, S. M. Ali Eslami, Aaron van den Oord
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Image completion, Object detection, Image classification
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
- 303M
- Training data
- tokens
source: https://openai.com/blog/image-gpt/#rfref25d
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
- Citations
- 1,556
"this unsupervised representation substantially improves transfer learning to object detection on the PASCAL VOC dataset, surpassing fully supervised pre-trained ImageNet classifiers"
Sources
Where this record came from and when it was last checked.
- Reference
- Data-Efficient Image Recognition with Contrastive Predictive Coding
- Last updated
- 25 May 2026
What the numbers mean
What this model is
CPC v2 was published by DeepMind,University of California (UC) Berkeley, in United Kingdom of Great Britain and Northern Ireland, in May 2019. industry,Academia is the category the publisher falls under.
It works in Vision, and is recorded as doing image completion, Object detection, Image classification.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
How it was trained
The reason it appears in this catalogue at all is sOTA improvement.
Answers
CPC v2 — common questions
Is CPC v2 open source?
No. CPC v2 has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does CPC v2 have?
CPC v2 has 303M parameters. source: https://openai.com/blog/image-gpt/#rfref25d. 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 CPC v2?
CPC v2 was published by DeepMind,University of California (UC) Berkeley, based in United Kingdom of Great Britain and Northern Ireland, categorised as industry,Academia.
When was CPC v2 released?
CPC v2 was published in May 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.
What is CPC v2 used for?
CPC v2 works in Vision, and is recorded as handling image completion, Object detection, Image classification. These are the areas it was designed around; they describe intent rather than a hard boundary.
What GPU do I need to run CPC v2?
None. CPC v2 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.