Llama 2 70B Chat

GPTKB entity

Statements (51)
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:bench gptkb:HellaSwag
gptkb:MMLU
gptkb:TruthfulQA
gptkb:ARC
gptkbp:context 4096 tokens
gptkbp:contrastsWith gptkb:PaLM_2
gptkb:GPT-3.5
Falcon 180B
gptkbp:developedBy gptkb:Meta_AI
gptkbp:fineTunedWith chat applications
gptkbp:hasModel decoder-only transformer
https://www.w3.org/2000/01/rdf-schema#label Llama 2 70B Chat
gptkbp:input gptkb:text
gptkbp:intendedUse research
commercial
gptkbp:language English
gptkbp:license custom commercial license
gptkbp:notableFeature reinforcement learning from human feedback
improved safety mechanisms
scalable to large deployments
supports function calling (with extensions)
supports multi-turn conversations
gptkbp:notableUser gptkb:researchers
developers
enterprises
gptkbp:openSource partially
gptkbp:optimizedFor gptkb:public_speaker
gptkbp:output gptkb:text
gptkbp:parameter 70 billion
gptkbp:partOf Llama 2 family
gptkbp:platform high-end GPUs
gptkbp:predecessor gptkb:Llama_1
gptkbp:releaseDate 2023
gptkbp:size 70B
gptkbp:successor Llama 3 (for some use cases)
gptkbp:supports code generation
question answering
summarization
conversational AI
instruction following
gptkbp:trainer reinforcement learning from human feedback
supervised fine-tuning
publicly available data sources
gptkbp:bfsParent gptkb:Llama_2_70B
gptkbp:bfsLayer 7