A generative world for general-purpose robotics & embodied AI learning.

Q&A dataset for many-shot jailbreaking

TOTALLY HARMLESS LIBERATION PROMPTS FOR GOOD LIL AI'S

Prompt Injection Primer for Engineers

Code release for Best-of-N Jailbreaking

Accelerated Quality-Diversity

A bare-bones Python library for quality diversity optimization.

Paired Open-Ended Trailblazer (POET) and Enhanced POET

A fast inference library for running LLMs locally on modern consumer-class GPUs

Universal and Transferable Attacks on Aligned Language Models

Granite Snack Cookbook -- easily consumable recipes (python notebooks) that showcase the capabilities of the Granite models

The source for REST API specifications for Microsoft Azure.

Covariance Matrix Adaptation Evolution Strategy (CMA-ES)

Generate large synthetic data using an LLM

DeMo: Decoupled Momentum Optimization

An interactive environment where protozoa-like entities live, die, and have offspring whose behaviours and morphologies can change.

A library for efficient similarity search and clustering of dense vectors.

Utilities intended for use with Llama models.

Google Deepmind's PromptBreeder for automated prompt engineering implemented in langchain expression language.

Unifying 3D Mesh Generation with Language Models

the LLM vulnerability scanner

PyTorch native post-training library

A syntax-highlighting pager for git, diff, grep, and blame output

Multi-platform high-performance compute language extension for Rust.

Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"

Taxonomy tree that will allow you to create models tuned with your data

Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

RefChecker provides automatic checking pipeline and benchmark dataset for detecting fine-grained hallucinations generated by Large Language Models.

A toolkit for fine-tuning, inferencing, and evaluating GreenBitAI's LLMs.