centerforaisafety

centerforaisafety

Geek Repo

Home Page:safe.ai/

Github PK Tool:Github PK Tool

centerforaisafety's repositories

HarmBench

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Language:Jupyter NotebookLicense:MITStargazers:191Issues:3Issues:31

tdc2023-starter-kit

This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.

Language:PythonLicense:MITStargazers:76Issues:6Issues:5

wmdp

WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning method which reduces LLM performance on WMDP while retaining general capabilities.

Language:Jupyter NotebookLicense:MITStargazers:46Issues:1Issues:8

AIS-cost-effectiveness

Cost-effectiveness models, tools, and results for various AI safety field-building programs.

Language:PythonLicense:MITStargazers:4Issues:0Issues:0

cerberus-cluster

HPC cluster code and configurations for running on OCI

Language:PythonLicense:UPL-1.0Stargazers:4Issues:0Issues:0
Language:Jupyter NotebookStargazers:3Issues:0Issues:0
Language:HTMLLicense:MITStargazers:2Issues:0Issues:0

prometheus-slurm-exporter

Prometheus exporter for performance metrics from Slurm.

Language:GoLicense:GPL-3.0Stargazers:1Issues:0Issues:6
Stargazers:1Issues:0Issues:0
Language:JavaScriptLicense:MITStargazers:1Issues:0Issues:0
Stargazers:0Issues:0Issues:0

trojan-dc-2022

Website for the Trojan Detection Challenge NeurIPS 2022 competition

Language:JavaScriptLicense:MITStargazers:0Issues:0Issues:0
Language:CSSLicense:MITStargazers:0Issues:0Issues:0

goslmailer

GoSlurmMailer - drop in replacement for default slurm MailProg. Delivers slurm job messages to various destinations.

Stargazers:0Issues:0Issues:0
Language:HTMLLicense:MITStargazers:0Issues:0Issues:0