JFChi
Follow
Highlights
- Pro
Stars
A trivial programmatic Llama 3 jailbreak. Sorry Zuck!
Papers and resources related to the security and privacy of LLMs 🤖
Hackable and optimized Transformers building blocks, supporting a composable construction.
ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors
We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20 via OpenAI’s APIs.
Building a quick conversation-based search demo with Lepton AI.
🐙 Guides, papers, lecture, notebooks and resources for prompt engineering
LlamaIndex is a data framework for your LLM applications
Multilingual safety benchmark for Large Language Models
Collection of scripts to aggregate image data for the purposes of training an NSFW Image Classifier
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
rotaryhammer / code-autodan
Forked from llm-attacks/llm-attacksAn unofficial implementation of AutoDAN attack on LLMs (arXiv:2310.15140)
Set of tools to assess and improve LLM security.
Reasoning in Large Language Models: Papers and Resources, including Chain-of-Thought, Instruction-Tuning and Multimodality.
Awesome-LLM: a curated list of Large Language Model
New ways of breaking app-integrated LLMs
A plug-and-play library for parameter-efficient-tuning (Delta Tuning)
Deal or No Deal? End-to-End Learning for Negotiation Dialogues
FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods.
Official implementation of the TabPFN paper (https://arxiv.org/abs/2207.01848) and the tabpfn package.
Awesome resources for in-context learning and prompt engineering: Mastery of the LLMs such as ChatGPT, GPT-3, and FlanT5, with up-to-date and cutting-edge updates.
OpenICL is an open-source framework to facilitate research, development, and prototyping of in-context learning.
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
Robust machine learning for responsible AI
Text perturbation methods to evaluate the robustness of NLP models
[ICML 2021] Towards Understanding and Mitigating Social Biases in Language Models