Lightweight Fine-tuning a Pretrained Protein Language Model for Protein Secondary

Closed weights Henan University March 2023

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
Henan University
Organisation type
Academia
Country
China
Published
23 March 2023
Authors
Wei Yang, Chun Liu, Zheng Li

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Biology
Task
Protein or nucleotide language model (pLM/nLM), Protein folding prediction
Base model
ProtT5-XL-U50

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
10,000,001 tokens

25,792 training chains × 400 residues = 10,316,800 tokens ≈ 1.0e7

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
1.9 × 10²² FLOP

1. Hardware setup: 1x NVIDIA GeForce RTX 3090 Ti (1.60 x 10^14 FP16 FLOP/s) 2. Training duration: Directly provided - 2,200 seconds/epoch × 43 epochs = 94,600 seconds 3. Utilization rate: 40% 4. Final calculation: 1.60 × 10^14 FLOP/s × 94,600 seconds × 0.4 = 6.05 × 10^18 FLOPs Base model: 18704498688000000000000 Total: 18704498688000000000000+6.05 × 10^18=18710548688000000000000

How it was established
Hardware
Fine-tuning compute
6.1 × 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 GeForce RTX 3090 Ti
Chips used
1
Wall-clock time
27 hours
Power draw
493 W

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
Lightweight Fine-tuning a Pretrained Protein Language Model for Protein Secondary Structure Prediction
Last updated
28 November 2025

What the numbers mean

Where it came from

Lightweight Fine-tuning a Pretrained Protein Language Model for Protein Secondary was published by Henan University, in China, in March 2023. academia is the category the publisher falls under.

It works in Biology, and is recorded as doing protein or nucleotide language model (pLM/nLM), Protein folding prediction.

It builds on ProtT5-XL-U50, which is why it shares that model's general shape and size.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

How it was trained

Producing it required around 1.9 × 10²² FLOP of arithmetic, on NVIDIA GeForce RTX 3090 Ti, which is a statement about the training budget rather than about inference.

The training set ran to roughly 10,000,001 tokens.

Answers

Lightweight Fine-tuning a Pretrained Protein Language Model for Protein Secondary — common questions

01

What GPU do I need to run Lightweight Fine-tuning a Pretrained Protein Language Model for Protein Secondary?

None. Lightweight Fine-tuning a Pretrained Protein Language Model for Protein Secondary 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.

02

Is Lightweight Fine-tuning a Pretrained Protein Language Model for Protein Secondary open source?

The licensing for Lightweight Fine-tuning a Pretrained Protein Language Model for Protein Secondary was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

03

How many parameters does Lightweight Fine-tuning a Pretrained Protein Language Model for Protein Secondary have?

No parameter count has been published for Lightweight Fine-tuning a Pretrained Protein Language Model for Protein Secondary, which is why no memory or speed figure appears on this page.

04

Who created Lightweight Fine-tuning a Pretrained Protein Language Model for Protein Secondary?

Lightweight Fine-tuning a Pretrained Protein Language Model for Protein Secondary was published by Henan University, based in China, categorised as academia.

05

When was Lightweight Fine-tuning a Pretrained Protein Language Model for Protein Secondary released?

Lightweight Fine-tuning a Pretrained Protein Language Model for Protein Secondary was published in March 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.

06

What is Lightweight Fine-tuning a Pretrained Protein Language Model for Protein Secondary used for?

Lightweight Fine-tuning a Pretrained Protein Language Model for Protein Secondary works in Biology, and is recorded as handling protein or nucleotide language model (pLM/nLM), Protein folding prediction. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

07

How much compute was used to train Lightweight Fine-tuning a Pretrained Protein Language Model for Protein Secondary?

Around 1.9 × 10²² FLOP, on NVIDIA GeForce RTX 3090 Ti. 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.

Source

Original publication

Record last updated 28 November 2025

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.