Llama 2 13B Instruct

GPTKB entity

Statements (48)
Predicate Object
gptkbp:instanceOf large language model
gptkbp:architecture gptkb:transformation
gptkbp:availableOn gptkb:Amazon_SageMaker
gptkb:Hugging_Face
gptkb:Meta_AI_website
gptkb:Microsoft_Azure
gptkbp:citation gptkb:Touvron_et_al.,_2023
gptkbp:context 4096 tokens
gptkbp:developedBy gptkb:Meta_AI
gptkbp:documentation available
gptkbp:family gptkb:Llama_2_70B
gptkb:Llama_2_34B
gptkb:Llama_2_7B
gptkbp:fineTunedWith instruction following
gptkbp:format plain text
gptkbp:hasModel decoder-only
https://www.w3.org/2000/01/rdf-schema#label Llama 2 13B Instruct
gptkbp:input gptkb:text
gptkbp:intendedUse research
commercial
gptkbp:language English
gptkbp:license custom commercial license
gptkbp:modelCard available
gptkbp:notableFeature improved performance over Llama 1
instruction-tuned variant
optimized for helpfulness and safety
gptkbp:openSource partially
gptkbp:output gptkb:text
gptkbp:parameter 13 billion
gptkbp:partOf Llama 2 family
gptkbp:platform GPU recommended
high memory requirement
gptkbp:predecessor gptkb:Llama_1
gptkbp:releaseDate 2023
gptkbp:size 13B
gptkbp:successor gptkb:Llama_3
gptkbp:supports question answering
summarization
text generation
chatbot applications
instruction following tasks
gptkbp:trainer publicly available data
Meta-licensed data
data from partners
reinforcement learning from human feedback
supervised fine-tuning
gptkbp:bfsParent gptkb:LLaMA_model_family
gptkbp:bfsLayer 8