SAVRN
Search Contact SAVRN

Open-weight model

plbart-base

by UCLA NLP uclanlp/plbart-base

plbart-base is an open-weight model from UCLA NLP. It has 1,024-token context. Its published files total 558.2 MB. It draws 120.9k downloads a month.

Parameters
Context1,024
Weights557.2 MB
License
AccessOpen weights
Monthly Downloads120.9k

Model Card

The publisher has not written a card for this model.

Configuration

Architecture
PLBartForConditionalGeneration
Context length (tokens)
1,024
Layers
6
Vocabulary size
50,005
Model type
plbart

Identity and Version

Repository
uclanlp/plbart-base
Publisher
UCLA NLP
Task
Not stated by the source
Modality
Other
Library
transformers
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
cf5287241fcff3819f6ade49635dc2d77efee032
First published
2022-03-02
Last updated
2021-11-09

Files and Weights

4 files, 558.2 MB in total. The weights are 1 file totalling 557.2 MB in bin.

Weights1 file · 557.2 MB
Configuration1 file · 783 B
Other1 file · 985.8 KB
Repository1 file · 1.2 KB
Every file
FileTypeSizeSHA-256
pytorch_model.binWeights557.2 MB 0464126e52fd
config.jsonConfiguration783 B
sentencepiece.bpe.modelOther985.8 KB f72f5d040a17
.gitattributesRepository1.2 KB

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
557.2 MB
Download from UCLA NLP

Released by UCLA NLP through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published557.2 MB

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

Questions About plbart-base

What is plbart-base's context length?

1,024 tokens, from the maximum position embeddings in its published configuration.