|
gptkbp:instanceOf
|
gptkb:large_language_model
|
|
gptkbp:architecture
|
gptkb:transformation
|
|
gptkbp:citation
|
gptkb:Touvron_et_al.,_2023
|
|
gptkbp:context
|
2048 tokens
|
|
gptkbp:developedBy
|
gptkb:Meta_AI
|
|
gptkbp:firstReleased
|
2023
|
|
gptkbp:input
|
gptkb:text
|
|
gptkbp:language
|
English
|
|
gptkbp:license
|
research only
|
|
gptkbp:notableEvent
|
weights leaked online in March 2023
|
|
gptkbp:notableFor
|
efficient performance on smaller hardware
competitive with larger models
|
|
gptkbp:openSource
|
partially
|
|
gptkbp:output
|
gptkb:text
|
|
gptkbp:parameter
|
13B
33B
65B
7B
|
|
gptkbp:predecessor
|
None
|
|
gptkbp:relatedTo
|
gptkb:Chinchilla
gptkb:GPT-3
gptkb:PaLM
gptkb:Llama_2
|
|
gptkbp:successor
|
gptkb:Llama_2
|
|
gptkbp:tokenizer
|
gptkb:Byte-Pair_Encoding
|
|
gptkbp:trainer
|
supervised learning
publicly available datasets
|
|
gptkbp:usedFor
|
gptkb:translator
natural language processing
question answering
summarization
text generation
chatbots
|
|
gptkbp:bfsParent
|
gptkb:LLaMA:_Open_and_Efficient_Foundation_Language_Models
|
|
gptkbp:bfsLayer
|
7
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
LLaMA language model
|