GovTech - AI Practice

Team

government

https://medium.com/dsaid-govtech

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

gabrielchua updated a dataset 4 days ago

govtech/CIRCLE

gabrielchua published a dataset 4 days ago

govtech/CIRCLE

gabrielchua updated a collection 15 days ago

Know Or Not 🤔

View all activity

Evaluate if a user prompt is on-topic for a given system prompt

Running

Biome

🍃

Multimodal search & retrieval-based biodiversity recognition

Running

System Prompt Leakage Demo

🚰

Evaluate system prompt leakage in LLM output

models 4

govtech/llama3-8b-sea-lionv2.1-instruct-secure

Text Generation • 8B • Updated Feb 20 • 16 • 2

govtech/stsb-roberta-base-off-topic

Updated Nov 25, 2024 • 11 • 2

govtech/jina-embeddings-v2-small-en-off-topic

Updated Nov 22, 2024 • 8 • 2

govtech/lionguard-v1

Updated Nov 16, 2024 • 156 • 9

datasets 3

govtech/CIRCLE

Viewer • Updated 4 days ago • 1.26k

govtech/PolicyBench

Preview • Updated 15 days ago • 83

govtech/MinorBench

Viewer • Updated Mar 14 • 299 • 51 • 4

GovTech - AI Practice

AI & ML interests

Recent Activity

Collections 6

Know Or Not: a library for evaluating out-of-knowledge base robustness

govtech/PolicyBench

govtech/MinorBench

MinorBench: A hand-built benchmark for content-based risks for children

Know Or Not: a library for evaluating out-of-knowledge base robustness

govtech/PolicyBench

govtech/MinorBench

MinorBench: A hand-built benchmark for content-based risks for children

spaces 3

Off Topic Guardrail Demo

Biome

System Prompt Leakage Demo

models 4

govtech/llama3-8b-sea-lionv2.1-instruct-secure

govtech/stsb-roberta-base-off-topic

govtech/jina-embeddings-v2-small-en-off-topic

govtech/lionguard-v1

datasets 3

govtech/CIRCLE

govtech/PolicyBench

govtech/MinorBench

AI & ML interests

Recent Activity

Team members 9

Collections 6

spaces 3 Sort: Recently updated

Off Topic Guardrail Demo

Biome

System Prompt Leakage Demo

models 4 Sort: Recently updated

datasets 3 Sort: Recently updated

spaces 3

models 4

datasets 3