|
gptkbp:instanceOf
|
large language model
|
|
gptkbp:alignment
|
gptkb:RLHF
Supervised Fine-Tuning
|
|
gptkbp:architecture
|
gptkb:transformation
|
|
gptkbp:availableOn
|
gptkb:Amazon_SageMaker
gptkb:Hugging_Face
gptkb:Microsoft_Azure
gptkb:Meta_AI
|
|
gptkbp:bench
|
gptkb:SQuAD
gptkb:TriviaQA
gptkb:BBH
gptkb:BoolQ
gptkb:GSM8K
gptkb:HellaSwag
gptkb:HumanEval
gptkb:MMLU
gptkb:OpenBookQA
gptkb:PIQA
gptkb:WinoGrande
gptkb:ARC
gptkb:DROP
|
|
gptkbp:citation
|
https://arxiv.org/abs/2404.14219
|
|
gptkbp:context
|
8K tokens
|
|
gptkbp:developer
|
gptkb:Meta_Platforms
|
|
gptkbp:format
|
gptkb:text
|
|
gptkbp:hasModel
|
decoder-only
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Meta Llama-3
|
|
gptkbp:language
|
English
multilingual
|
|
gptkbp:license
|
custom commercial license
|
|
gptkbp:notableFeature
|
multilingual support
improved reasoning
better code generation
open weights for research
|
|
gptkbp:notableUser
|
gptkb:Amazon_Web_Services
gptkb:Hugging_Face_community
gptkb:Microsoft_Azure_AI
Meta AI Assistant
|
|
gptkbp:officialWebsite
|
https://ai.meta.com/llama/
|
|
gptkbp:openSource
|
false
|
|
gptkbp:parameter
|
70B
8B
|
|
gptkbp:predecessor
|
gptkb:Llama_2
|
|
gptkbp:releaseDate
|
2024-04-18
|
|
gptkbp:supportsFineTuning
|
true
|
|
gptkbp:trainingDataCutoff
|
2023-03
|
|
gptkbp:trainingDataSize
|
15T tokens
|
|
gptkbp:trainingObjective
|
next token prediction
|
|
gptkbp:uses
|
chatbot
translator
reasoning
code generation
summarization
text generation
|
|
gptkbp:bfsParent
|
gptkb:Nous_Hermes_2_Llama-3
|
|
gptkbp:bfsLayer
|
7
|