Statements (30)
| 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:developedBy |
gptkb:Meta_AI
|
| gptkbp:family |
gptkb:Llama_2
|
| gptkbp:fineTunedWith |
conversational tasks
|
| gptkbp:hasModel |
decoder-only
|
| https://www.w3.org/2000/01/rdf-schema#label |
Llama 2 70B Instruct
|
| gptkbp:input |
4096 tokens
|
| gptkbp:language |
English
|
| gptkbp:license |
custom commercial license
|
| gptkbp:notableFor |
high performance on benchmarks
|
| gptkbp:openSource |
partially
|
| gptkbp:parameter |
70 billion
|
| gptkbp:purpose |
instruction following
|
| gptkbp:releaseDate |
2023
|
| gptkbp:size |
70B
|
| gptkbp:successor |
gptkb:Llama_1
|
| gptkbp:supports |
code generation
question answering summarization text generation |
| gptkbp:trainer |
publicly available data
reinforcement learning from human feedback supervised fine-tuning |
| gptkbp:bfsParent |
gptkb:LLaMA_model_family
|
| gptkbp:bfsLayer |
8
|