SoyGema

concordia

A library for generative social simulation

baml

BAML is a language that helps you get structured data from LLMs, with the best DX possible. Works with all languages. Check out the promptfiddle.com playground

LLM_MultiAgents_Survey_Papers

Large Language Model based Multi-Agents: A Survey of Progress and Challenges

prompt-poet

Streamlines and simplifies prompt design for both developers and non-technical users with a low code approach.

Interactive_Tools

Interactive Tools for Machine Learning, Deep Learning and Math

open-webui

User-friendly WebUI for AI (Formerly Ollama WebUI)

CritiqueLLM

mem0

The Memory layer for your AI apps

penzai

A JAX research toolkit for building, editing, and visualizing neural networks.

manim

A community-maintained Python framework for creating mathematical animations.

meltingpot-2023-solution

Melting Pot 2023 Challenge Solution

Melting-Pot-Contest-2023

awesome-ai-agents

A list of AI autonomous agents

meltingpot

A suite of test scenarios for multi-agent reinforcement learning.

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.

awesome-RLHF

A curated list of reinforcement learning with human feedback resources (continually updated)

mamba

Mamba SSM architecture

transformer-debugger

lit

The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.

Ditto

A self-ailgnment method for role-play. Benchmark for role-play. Resources for "Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment".

py2puml

Generate PlantUML class diagrams to document your Python application.

pydeps

Python Module Dependency graphs

FriendsDontLetFriends

Friends don't let friends make certain types of data visualization - What are they and why are they bad.

cve-maker

Tool to find CVEs and Exploits.

jupyter-ai

A generative AI extension for JupyterLab

omnisafe

JMLR: OmniSafe is an infrastructural framework for accelerating SafeRL research.

promptbench

A unified evaluation framework for large language models

safety-gymnasium

NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark

skrub

Prepping tables for machine learning

exploit_mitigations

Knowledge base of exploit mitigations available across numerous operating systems, architectures and applications and versions.