ProteinDT
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
- University of California (UC) Berkeley,California Institute of Technology,University of Toronto,University of Wisconsin Madison,Texas A&M,NVIDIA,Mila - Quebec AI (originally Montreal Institute for Learning Algorithms)
- Organisation type
- Academia,Academia,Academia,Academia,Academia,Industry,Academia
- Country
- United States of America, Canada
- Published
- 9 February 2023
- Authors
- Shengchao Liu, Yanjing Li, Zhuoxinran Li, Anthony Gitter, Yutao Zhu, Jiarui Lu, Zhao Xu, Weili Nie, Arvind Ramanathan, Chaowei Xiao, Jian Tang, Hongyu Guo, and Anima Anandkumar
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology, Language
- Task
- Proteins, Protein representation learning, Protein generation, Protein design
- Base model
- SciBERT
- 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
- 132,303,900 tokens
Total amino acids: 197,000,000 residues Final calculation: 1.97 × 10⁸ datapoints Value = 197,000,000 = 1.97e8
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/chao1224/ProteinDT
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
- Record confidence
- Likely
"Compared to six state-of-the-art protein sequence representation methods, ProteinDT can obtain consistently superior performance on four of six benchmark tasks."
Sources
Where this record came from and when it was last checked.
- Reference
- A Text-guided Protein Design Framework
- Last updated
- 28 November 2025
What the numbers mean
What this model is
ProteinDT was published by University of California (UC) Berkeley,California Institute of Technology,University of Toronto,University of Wisconsin Madison,Texas A&M,NVIDIA,Mila - Quebec AI (originally Montreal Institute for Learning Algorithms), in United States of America, in February 2023. academia,Academia,Academia,Academia,Academia,Industry,Academia is the category the publisher falls under.
It works in Biology, Language, and is recorded as doing proteins, Protein representation learning, Protein generation, Protein design.
It is derived from SciBERT rather than trained from scratch, which is the usual way a specialised model is produced.
The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold.
How it was trained
The training set ran to roughly 132,303,900 tokens.
The reason it appears in this catalogue at all is sOTA improvement.
Answers
ProteinDT — common questions
What GPU do I need to run ProteinDT?
We cannot say. ProteinDT 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 ProteinDT open source?
Its weights are published, so ProteinDT 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 ProteinDT have?
No parameter count has been published for ProteinDT, which is why no memory or speed figure appears on this page.
Who created ProteinDT?
ProteinDT was published by University of California (UC) Berkeley,California Institute of Technology,University of Toronto,University of Wisconsin Madison,Texas A&M,NVIDIA,Mila - Quebec AI (originally Montreal Institute for Learning Algorithms), based in United States of America, categorised as academia,Academia,Academia,Academia,Academia,Industry,Academia.
When was ProteinDT released?
ProteinDT was published in February 2023. 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 ProteinDT used for?
ProteinDT works in Biology, Language, and is recorded as handling proteins, Protein representation learning, Protein generation, Protein design. 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 ProteinDT?
The weights for ProteinDT are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
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.