SimCSE
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
- Princeton University,Tsinghua University
- Organisation type
- Academia,Academia
- Country
- United States of America, China
- Published
- 18 May 2022
- Authors
- Tianyu Gao, Xingcheng Yao, Danqi Chen
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Semantic embedding
- Base model
- RoBERTa Large
- Numerical format
- FP16
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
- 27,363,505 tokens
- Epochs
- 3
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
- Hugging Face
- princeton-nlp
Unclear lisense: https://huggingface.co/princeton-nlp/sup-simcse-roberta-large MIT license: https://github.com/princeton-nlp/SimCSE?tab=readme-ov-file
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
- Highly cited,SOTA improvement
- Record confidence
- Likely
- Citations
- 4,419
"We evaluate SimCSE on standard semantic textual similarity (STS) tasks, and our unsupervised and supervised models using BERT base achieve an average of 76.3% and 81.6% Spearman's correlation respectively, a 4.2% and 2.2% improvement compared to the previous best results." Table 5
Sources
Where this record came from and when it was last checked.
- Reference
- SimCSE: Simple Contrastive Learning of Sentence Embeddings
- Last updated
- 25 May 2026
What the numbers mean
What this model is
SimCSE was published by Princeton University,Tsinghua University, in United States of America, in May 2022. It comes out of academia,Academia.
It works in Language, and is recorded as doing semantic embedding.
Its starting point was RoBERTa Large — most models at this scale are adapted from an existing base rather than built from nothing.
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. It is published under the princeton-nlp organisation on Hugging Face.
Training and provenance
The training set ran to roughly 27,363,505 tokens.
Its inclusion criterion is highly cited,SOTA improvement.
Answers
SimCSE — common questions
What is SimCSE used for?
SimCSE works in Language, and is recorded as handling semantic embedding. 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 SimCSE?
Its weights are published under the princeton-nlp organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.
What GPU do I need to run SimCSE?
We cannot say. SimCSE 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 SimCSE open source?
Its weights are published, so SimCSE 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 SimCSE have?
No parameter count has been published for SimCSE, which is why no memory or speed figure appears on this page.
Who created SimCSE?
SimCSE was published by Princeton University,Tsinghua University, based in United States of America, categorised as academia,Academia.
When was SimCSE released?
SimCSE was published in May 2022. 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.