GeoSeqBuilder
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
- Peking University
- Organisation type
- Academia
- Country
- China
- Published
- 19 September 2024
- Authors
- Jiale Liu, Zheng Guo, Hantian You, Changsheng Zhang, Luhua Lai
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- Protein design, Protein generation
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
- 35,250,000 tokens
Training datapoints = Training proteins × Average residues per protein 23,500 × 200 = 4,700,000 datapoints Final estimate: 4.7 million datapoints
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
- 6.5 × 10¹⁸ FLOP
- How it was established
- Hardware
1. Hardware: 1x NVIDIA A30 GPU (1.50×10¹⁴ FLOP/s using fp16 tensor cores) 2. Training duration: Directly provided - 15 epochs × 2 hours/epoch = 30 hours = 108,000 seconds 3. Utilization rate: 40% 4. Calculation: 1.50×10¹⁴ FLOP/s × 1 GPU × 108,000s × 0.40 = 6.48×10¹⁸ 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 A30 PCIe
- Chips used
- 1
- Wall-clock time
- 30 hours
- Power draw
- 179 W
Training duration: Directly provided - 15 epochs × 2 hours/epoch = 30 hours = 108,000 seconds
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 (non-commercial)
- Training code
- Unreleased
no clear license https://github.com/PKUliujl/GeoSeqBuilder
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
- 1
Sources
Where this record came from and when it was last checked.
- Reference
- All-Atom Protein Sequence Design Based on Geometric Deep Learning
- Last updated
- 28 November 2025
What the numbers mean
Background
GeoSeqBuilder was published by Peking University, in the country recorded as China, during September 2024. The category the publisher falls under is academia.
It works in the domain of Biology, and is recorded as performing the task of protein design, Protein generation.
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.
What went into building it
Producing it required arithmetic totalling around 6.5 × 10¹⁸ FLOP, on hardware recorded as NVIDIA A30 PCIe. That figure measures what producing the model cost, and has no bearing on how fast it answers.
The training set ran to roughly 35,250,000 tokens of text.
Answers
GeoSeqBuilder — common questions
GeoSeqBuilder— how much compute was used to train it?
Training consumed around 6.5 × 10¹⁸ FLOP, on hardware recorded as NVIDIA A30 PCIe. 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.
GeoSeqBuilder— what GPU do I need to run it?
We cannot say. It 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.
GeoSeqBuilder— is it open source?
Its weights are published, so it 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.
GeoSeqBuilder— how many parameters does it have?
No parameter count has been published for it, which is why no memory or speed figure appears on this page.
GeoSeqBuilder— who created it?
It was published by Peking University, based in China, an organisation categorised as academia.
GeoSeqBuilder— when was it released?
It was published in September 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.
GeoSeqBuilder— what is it used for?
It works in the domain of Biology, and is recorded as handling the task of protein design, Protein generation. These are the areas it was designed around; they describe intent rather than a hard boundary.
GeoSeqBuilder— where can I download it?
The weights 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.