Statements (22)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:model
|
| gptkbp:availableOn |
gptkb:Hugging_Face
|
| gptkbp:category |
content filtering
AI safety |
| gptkbp:compatibleWith |
gptkb:Llama_2
gptkb:Llama_3 |
| gptkbp:developedBy |
gptkb:Meta
|
| gptkbp:documentation |
https://llama.meta.com/llama-guard/
|
| gptkbp:hasModel |
moderation model
|
| gptkbp:input |
gptkb:text
|
| gptkbp:language |
English
|
| gptkbp:license |
Meta license
|
| gptkbp:openSource |
true
|
| gptkbp:output |
text classification
|
| gptkbp:purpose |
content moderation
safety filtering |
| gptkbp:releaseYear |
2023
|
| gptkbp:usedFor |
moderating model outputs
moderating user prompts |
| gptkbp:bfsParent |
gptkb:LLaMA_model_family
|
| gptkbp:bfsLayer |
8
|
| https://www.w3.org/2000/01/rdf-schema#label |
Llama Guard
|