sgRNAGen
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
- Beijing Institute of Technology
- Organisation type
- Academia
- Country
- China
- Published
- 31 May 2024
- Authors
- Yan Xia, Zeyu Liang, Xiaowen Du, Dengtian Cao, Jing Li, Lichao Sun, Yi-Xin Huo, Shuyuan Guo
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- RNA design
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
- 14.2M
- Training data
- tokens
" with our model comprising 8 layers and 12 heads. " "The vocabulary of sgRNAGen encompasses383 seven tokens: A, T, C, G, and special tokens such as [PAD], [MASK], and [UNK]" "The hidden size386 was set as 384" 8 layers, 12 heads, vocab of 7, d_model of 384 d_head=384/12=32 Attention parameters: 12*(384*(2*32+32)+32*384)=589824 MLP = 384*4*384*2= 1179648 Total: 7*382+8*(589824+1179648)=14158450
"40,000 CRISPR-related129 RNA sequences have been utilized for training the sgRNAGen model" Generated test cases are 61 tokens, assuming this also applies to training data 40000*61=2440000
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
- Design nonrepetitive and diverse activity single-guide RNA by deep learning
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
sgRNAGen was published by Beijing Institute of Technology, in China, in May 2024. The organisation is categorised as academia.
It works in Biology, and is recorded as doing rNA design.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
Answers
sgRNAGen — common questions
Is sgRNAGen open source?
The licensing for sgRNAGen was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
How many parameters does sgRNAGen have?
sgRNAGen has 14.2M parameters. " with our model comprising 8 layers and 12 heads. " "The vocabulary of sgRNAGen encompasses383 seven tokens: A, T, C, G, and special tokens such as [PAD], [MASK], and [UNK]" "The hidden size386 was set as 384" 8 layers, 12 heads, vocab of 7, d_model of 384 d_head=384/12=32 Attention parameters: 12*(384*(2*32+32)+32*384)=589824 MLP = 384*4*384*2= 1179648 Total: 7*382+8*(589824+1179648)=14158450. 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 sgRNAGen?
sgRNAGen was published by Beijing Institute of Technology, based in China, categorised as academia.
When was sgRNAGen released?
sgRNAGen was published in May 2024. 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 sgRNAGen used for?
sgRNAGen works in Biology, and is recorded as handling rNA 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.
What GPU do I need to run sgRNAGen?
None. sgRNAGen 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.