amnaBooq

amnaBooq's Stars

• Yu-Fangxu/COLD-Attack

  Official code of "COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability" (ICML 2024)

  Language:Python5813

• YihanWang617/llm-jailbreaking-defense

  A lightweight library for large laguage model (LLM) jailbreaking defense.

  Language:Python161

• XHMY/AutoDefense

  AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks

  Language:Python184

• poloclub/llm-self-defense

  LLM Self Defense: By Self Examination, LLMs know they are being tricked

  Language:Python121

• CallumMoss/Mitigating_Backdoor_Attacks_in_LLMs

  2 Python programmes used for detecting and preventing backdoor attacks in large language models.

  Language:Python1

• lancedb/vectordb-recipes

  High quality resources & applications for LLMs, multi-modal models and VectorDBs

  Language:Jupyter Notebook49286

• lyuchenyang/Macaw-LLM

  Macaw-LLM: Multi-Modal Language Modeling with Image, Video, Audio, and Text Integration

  Language:Python1.5k115

• modelscope/agentscope

  Start building LLM-empowered multi-agent applications in an easier way.

  Language:Python2.9k194

• ltroin/llm_attack_defense_arena

  Language:Python634

• OpenBMB/ChatDev

  Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)

  Language:Shell24.4k3.1k

• TigerResearch/TigerBot

  TigerBot: A multi-language multi-task LLM

  Language:Python2.2k195

• langroid/langroid

  Harness LLMs with Multi-Agent Programming

  Language:Python1.9k189

• geekan/MetaGPT

  🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

  Language:Python41.4k4.9k

• aws-samples/aws-genai-llm-chatbot

  A modular and comprehensive solution to deploy a Multi-LLM and Multi-RAG powered chatbot (Amazon Bedrock, Anthropic, HuggingFace, OpenAI, Meta, AI21, Cohere, Mistral) using AWS CDK on AWS

  Language:TypeScript967284

• simonw/llm-mistral

  LLM plugin providing access to Mistral models using the Mistral API

  Language:Python13212

• ollama/ollama

  Get up and running with Llama 3, Mistral, Gemma 2, and other large language models.

  Language:Go77k5.8k

• open-compass/MixtralKit

  A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI

  Language:Python76381

• katanaml/llm-mistral-invoice-cpu

  Data extraction with LLM on CPU

  Language:Python24953

• hiyouga/LLaMA-Factory

  Unify Efficient Fine-Tuning of 100+ LLMs

  Language:Python25.7k3.2k

• aiplaybookin/novice-ChatGPT

  ChatGPT API Usage using LangChain, LlamaIndex, Guardrails, AutoGPT and more

  Language:Jupyter Notebook12416

• wenqiglantz/DevSecOpsKB-LlamaIndex-LangChain-OpenAI

  DevSecOps knowledge base chatbot built with LlamaIndex, LangChain, and OpenAI

  Language:Python9626

• carolinedlu/llamaindex-chat-with-streamlit-docs

  Build a chatbot powered by LlamaIndex that augments GPT 3.5 with the contents of the Streamlit docs (or your own data).

  Language:Python167228

• run-llama/llama_index

  LlamaIndex is a data framework for your LLM applications

  Language:Python33.3k4.7k

• chris-koch-penn/gpt3_security_vulnerability_scanner

  GPT-3 found hundreds of security vulnerabilities in this repo

  Language:PHP59297

• RayRuiboChen/JailbreakGPT4v

  Code for Jailbreak GPT-4Vision: an empirical study on baseline attacks and defenses

  Language:Python1

• mujtaba057/LAW-BOT-Legal-Strategy-Companion---AI-for-Case-Studies-Advice-Law-Insights-

  Streamlit application Provided defense points on specific allegations against an individual mentioned in the uploaded documents using Langchain-and-OpenAI-API-LLM-model-and-embeddings-vector-database

  Language:Python3

• Palak-B/Watermarking-LLMs-Identifying-and-Preventing-Attacks

  The project seeks to create defense systems against insertion attacks and contribute to the responsible and secure use of LLMs

  Language:Python1

• arnavkomaragiri/LLM-Gradient-Attack-Defense

  Analyzing behavior of LLMs under gradient-based adversarial attacks and developing countermeasures during model fine-tuning

  Language:Python1

• youmustfight/gideon

  LLM/Multi-Modal Tooling for Lawyers doing Public Defense/Refugee Assistance

  Language:Python5

• redwoodresearch/Text-Steganography-Benchmark

  Code for Preventing Language Models From Hiding Their Reasoning, which evaluates defenses against LLM steganography.

  Language:Python123