|
gptkbp:instanceOf
|
gptkb:large_language_model
|
|
gptkbp:architecture
|
gptkb:transformation
|
|
gptkbp:availableOn
|
gptkb:Hugging_Face
|
|
gptkbp:contextWindowSize
|
2048 tokens
|
|
gptkbp:countryOfOrigin
|
gptkb:United_Arab_Emirates
|
|
gptkbp:developedBy
|
gptkb:Technology_Innovation_Institute
|
|
gptkbp:hardware
|
high-end GPUs
|
|
gptkbp:hasModel
|
decoder-only
|
|
gptkbp:intendedUse
|
gptkb:research
commercial
educational
|
|
gptkbp:language
|
English
|
|
gptkbp:license
|
Apache 2.0
|
|
gptkbp:notableFor
|
largest openly released language model as of 2023
|
|
gptkbp:openSource
|
true
|
|
gptkbp:organization
|
gptkb:research_institute
|
|
gptkbp:parameter
|
180 billion
|
|
gptkbp:predecessor
|
gptkb:Falcon-40B
|
|
gptkbp:releaseDate
|
September 2023
|
|
gptkbp:supports
|
code generation
question answering
summarization
text generation
text completion
|
|
gptkbp:trainingDataSize
|
3.5 trillion tokens
|
|
gptkbp:trainingDataType
|
books
web data
conversational data
refined web corpus
|
|
gptkbp:trainingFramework
|
gptkb:PyTorch
|
|
gptkbp:bfsParent
|
gptkb:Falcon_LLM
|
|
gptkbp:bfsLayer
|
8
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Falcon-180B
|