PMLM-large

Closed weights Microsoft Research Asia,Nanyang Technological University,Xi’an Jiaotong University,Sun Yat-sen University 250M parameters October 2021

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
Microsoft Research Asia,Nanyang Technological University,Xi’an Jiaotong University,Sun Yat-sen University
Organisation type
Industry,Academia,Academia,Academia
Country
China, Singapore
Published
21 October 2021
Authors
Liang He, Shizhuo Zhang, Lijun Wu, Huanhuan Xia, Fusong Ju, He Zhang, Siyuan Liu, Yingce Xia, Jianwei Zhu, Pan Deng, Bin Shao, Tao Qin, Tie-Yan Liu

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)

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
250M

"Following the RoBERTa-base setting, the hidden size, feed forward dimension, number of encoder layers, and attention heads of the base models are set as 768, 3072, 12, 12 re- spectively (denoted as MLM-base for MLM and PMLM-base for PMLM). A larger model named PMLM-large is pre-trained with the same setting except using 34 as the number of encoder layers."

Training data
tokens

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
3.8 × 10²¹ FLOP

1176*60*60*125000000000000*24*0.3=3.81024e+21

How it was established
Hardware

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 V100
Chips used
24
Wall-clock time
1,176 hours (49 days)

"about seven weeks for PMLM-large"

Power draw
14.5 kW

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
36

Sources

Where this record came from and when it was last checked.

Reference
Pre-Training Co-Evolutionary Protein Representation via a Pairwise Masked Language Model
Last updated
25 May 2026

What the numbers mean

Where it came from

PMLM-large was published by Microsoft Research Asia,Nanyang Technological University,Xi’an Jiaotong University,Sun Yat-sen University, in the country recorded as China, during October 2021. The category the publisher falls under is industry,Academia,Academia,Academia.

It works in the domain of Biology, and is recorded as performing the task of protein or nucleotide language model (pLM/nLM).

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

What went into building it

The training run consumed about 3.8 × 10²¹ FLOP, on hardware recorded as NVIDIA V100. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Answers

PMLM-large — common questions

01

PMLM-large— what GPU do I need to run it?

None. This 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

PMLM-large— is it open source?

The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

03

PMLM-large— how many parameters does it have?

It has a parameter count of 250M. "Following the RoBERTa-base setting, the hidden size, feed forward dimension, number of encoder layers, and attention heads of the base models are set as 768, 3072, 12, 12 re- spectively (denoted as MLM-base for MLM and PMLM-base for PMLM). A larger model named PMLM-large is pre-trained with the same setting except using 34 as the number of encoder layers.". 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.

04

PMLM-large— who created it?

It was published by Microsoft Research Asia,Nanyang Technological University,Xi’an Jiaotong University,Sun Yat-sen University, based in China, an organisation categorised as industry,Academia,Academia,Academia.

05

PMLM-large— when was it released?

It was published in October 2021. 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

PMLM-large— what is it used for?

It works in the domain of Biology, and is recorded as handling the task of protein or nucleotide language model (pLM/nLM). 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.

07

PMLM-large— how much compute was used to train it?

Training consumed around 3.8 × 10²¹ FLOP, on hardware recorded as NVIDIA V100. 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 25 May 2026

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.