GPT-2-Medium+Pixelfly
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
- Stanford University,SambaNova Systems, Inc,Peking University,Adobe,University at Buffalo
- Organisation type
- Academia,Industry,Academia,Industry,Academia
- Country
- United States of America, China
- Published
- 30 November 2021
- Authors
- Tri Dao, Beidi Chen, Kaizhao Liang, Jiaming Yang, Zhao Song, Atri Rudra, Christopher Ré
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Language modeling, Text 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
- 203M
- Training data
- 103,000,000 tokens
- Epochs
- 100
203M (Table 6)
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
- 1.3 × 10¹⁹ FLOP
- How it was established
- Operation counting
6 FLOP / parameter / token * 203000000 parameters * 103000000 tokens * 100 epochs = 1.25454 × 10^19 FLOP
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 V100
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
apache for code (train and inference): https://github.com/HazyResearch/fly train code: https://github.com/HazyResearch/fly/blob/master/src/train.py
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
- 94
- Benchmark data
- GPT-2-Medium+Pixelfly
Sources
Where this record came from and when it was last checked.
- Reference
- Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models
- Last updated
- 25 May 2026
What the numbers mean
Where it came from
GPT-2-Medium+Pixelfly was published by Stanford University,SambaNova Systems, Inc,Peking University,Adobe,University at Buffalo, in United States of America, in November 2021. academia,Industry,Academia,Industry,Academia is the category the publisher falls under.
It works in Language, and is recorded as doing language modeling, Text classification.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Training and provenance
The training run consumed about 1.3 × 10¹⁹ FLOP, on NVIDIA V100. That figure describes the cost of creating it and has no bearing on how quickly it generates text.
The training set ran to roughly 103,000,000 tokens.
Answers
GPT-2-Medium+Pixelfly — common questions
How many parameters does GPT-2-Medium+Pixelfly have?
GPT-2-Medium+Pixelfly has 203M parameters. 203M (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 GPT-2-Medium+Pixelfly?
GPT-2-Medium+Pixelfly was published by Stanford University,SambaNova Systems, Inc,Peking University,Adobe,University at Buffalo, based in United States of America, categorised as academia,Industry,Academia,Industry,Academia.
When was GPT-2-Medium+Pixelfly released?
GPT-2-Medium+Pixelfly was published in November 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.
What is GPT-2-Medium+Pixelfly used for?
GPT-2-Medium+Pixelfly works in Language, and is recorded as handling language modeling, Text classification. These are the areas it was designed around; they describe intent rather than a hard boundary.
How much compute was used to train GPT-2-Medium+Pixelfly?
Around 1.3 × 10¹⁹ FLOP, on NVIDIA V100. 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 GPT-2-Medium+Pixelfly?
None. GPT-2-Medium+Pixelfly 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 GPT-2-Medium+Pixelfly open source?
No. GPT-2-Medium+Pixelfly has not had its weights published, so it exists only as a service controlled by its owner.
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.