LetheSec

circuit-breakers

L1B3RT45

J41LBR34K PR0MPT5 F0R 4LL M4J0R LLM5

SOUL

Official repo for paper "SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning"

self-rewarding-lm-pytorch

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

llama3

The official Meta Llama 3 GitHub site

negative-preference-optimization

llm_unlearn

LLM Unlearning

tofu

Landing Page for TOFU

awesome-machine-unlearning

Awesome Machine Unlearning (A Survey of Machine Unlearning)

LLM_unlearning

awesome-llm-unlearning

A resource repository for machine unlearning in large language models

llm-adaptive-attacks

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]

LLM-Safeguard

Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"

chat_templates

Chat Templates for 🤗 HuggingFace Large Language Models

rpo

Official repository for paper, "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"

llm_attack_defense_arena

MoneyPrinterTurbo

利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.

DeepLearing-Interview-Awesome-2024

AIGC-interview/CV-interview/LLMs-interview面试问题与答案集合仓，同时包含工作和科研过程中的新想法、新问题、新资源与新项目

grok-1

Grok open release

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

ICD

Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced Hallucinations"

EasyJailbreak

An easy-to-use Python framework to generate adversarial jailbreak prompts.

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

transformer-debugger

ShadowAlignment

Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models

weak-to-strong

Weak-to-Strong Jailbreaking on Large Language Models

CLIPInversion

What do we learn from inverting CLIP models?

LLaMA-Factory

Unify Efficient Fine-Tuning of 100+ LLMs

llm-attacks

Universal and Transferable Attacks on Aligned Language Models

SafeDecoding

Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding