SAVRN
Search Contact SAVRN

Open-weight model

prot_t5_xl_uniref50

by Rostlab Rostlab/prot_t5_xl_uniref50

Pretrained model on protein sequences using a masked language modeling (MLM) objective. It was introduced in this paper and first released in this repository. This model is trained on uppercase amino acids: it only works with capital letter amino acids.

Parameters
Context
Weights33.8 GB
License
AccessOpen weights
Monthly Downloads179.2k

Model Card

Pretrained model on protein sequences using a masked language modeling (MLM) objective. It was introduced in this paper and first released in this repository. This model is trained on uppercase amino acids: it only works with capital letter amino acids. ProtT5-XL-UniRef50 is based on the t5-3b model and was pretrained on a large corpus of protein sequences in a self-supervised fashion. This means it was pretrained on the raw protein sequences only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those protein sequences. One important difference between this T5 model and the…

Excerpt from the card by Rostlab.

Configuration

Architecture
T5ForConditionalGeneration
Vocabulary size
128
Model type
t5

Identity and Version

Repository
Rostlab/prot_t5_xl_uniref50
Publisher
Rostlab
Task
Not stated by the source
Modality
Other
Library
transformers
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
973be27c52ee6474de9c945952a8008aeb2a1a73
First published
2022-03-02
Last updated
2023-01-31

Files and Weights

9 files, 33.8 GB in total. The weights are 3 files totalling 33.8 GB in bin.

Weights3 files · 33.8 GB
Configuration2 files · 2.3 KB
Tokenizer2 files · 238.0 KB
Documentation1 file · 7.6 KB
Repository1 file · 690 B
Every file
FileTypeSizeSHA-256
pytorch_model.binWeights11.3 GB c06141d42e93
pytorch_model_600k.binWeights11.3 GB e7f35dee1572
pytorch_model_723k.binWeights11.3 GB 6f2fb2f30a59
config.jsonConfiguration546 B
special_tokens_map.jsonConfiguration1.8 KB
README.mdDocumentation7.6 KB
.gitattributesRepository690 B
spiece.modelTokenizer238.0 KB 74da7b4afcde
tokenizer_config.jsonTokenizer24 B

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
33.8 GB
Download from Rostlab

Released by Rostlab through its official repository on Hugging Face.

Built From

  • Trained on (disclosed) UniRef50

Memory Requirements

PrecisionWeights in memory
As published33.8 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.