This repository provides an original implementation of Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications. It includes tools for neuron-level pruning, pruning based on set difference, Wanda/SNIP score dumping, rank-level pruning, and rank removal with orthogonal projection. Users can specify parameters like prune method, datasets, sparsity ratio, model, and save location to evaluate and modify neural networks for safety alignment.

ML-Bench is a tool designed to evaluate large language models and agents for machine learning tasks on repository-level code. It provides functionalities for data preparation, environment setup, usage, API calling, open source model fine-tuning, and inference. Users can clone the repository, load datasets, run ML-LLM-Bench, prepare data, fine-tune models, and perform inference tasks. The tool aims to facilitate the evaluation of language models and agents in the context of machine learning tasks on code repositories.

ICE-Score is a tool designed to instruct large language models to evaluate code. It provides a minimum viable product (MVP) for evaluating generated code snippets using inputs such as problem, output, task, aspect, and model. Users can also evaluate with reference code and enable zero-shot chain-of-thought evaluation. The tool is built on codegen-metrics and code-bert-score repositories and includes datasets like CoNaLa and HumanEval. ICE-Score has been accepted to EACL 2024.

This is a vulnerability mining engine purely based on GPT, requiring no prior knowledge base, no fine-tuning, yet its effectiveness can overwhelmingly surpass most of the current related research. The core idea revolves around being task-driven, not question-driven, driven by prompts, not by code, and focused on prompt design, not model design. The essence is encapsulated in one word: deception. It is a type of code understanding logic vulnerability mining that fully stimulates the capabilities of GPT, suitable for real actual projects.

This repository contains a vulnerability mining engine based on GPT technology. The engine is designed to identify logic vulnerabilities in code by utilizing task-driven prompts. It does not require prior knowledge or fine-tuning and focuses on prompt design rather than model design. The tool is effective in real-world projects and should not be used for academic vulnerability testing. It supports scanning projects in various languages, with current support for Solidity. The engine is configured through prompts and environment settings, enabling users to scan for vulnerabilities in their codebase. Future updates aim to optimize code structure, add more language support, and enhance usability through command line mode. The tool has received a significant audit bounty of $50,000+ as of May 2024.

PrefixQuant is an official PyTorch implementation for static quantization that outperforms dynamic quantization in Large Language Models (LLMs) by utilizing prefixed outliers. The tool provides functionalities for quantization, inference, and visualization of activation distributions. Users can fine-tune quantization settings and evaluate pre-quantized models for tasks like PIQA, ARC, Hellaswag, and Winogrande. The approach aims to improve performance and efficiency in LLMs through innovative quantization techniques.

Hurley AI is a next-gen framework for developing intelligent agents through Retrieval-Augmented Generation. It enables easy creation of custom AI assistants and agents, supports various agent types, and includes pre-built tools for domains like finance and legal. Hurley AI integrates with LLM inference services and provides observability with Arize Phoenix. Users can create Hurley RAG tools with a single line of code and customize agents with specific instructions. The tool also offers various helper functions to connect with Hurley RAG and search tools, along with pre-built tools for tasks like summarizing text, rephrasing text, understanding memecoins, and querying databases.

Mergekit is a toolkit for merging pre-trained language models. It uses an out-of-core approach to perform unreasonably elaborate merges in resource-constrained situations. Merges can be run entirely on CPU or accelerated with as little as 8 GB of VRAM. Many merging algorithms are supported, with more coming as they catch my attention.

The `vectara-agentic` Python library is designed for developing powerful AI assistants using Vectara and Agentic-RAG. It supports various agent types, includes pre-built tools for domains like finance and legal, and enables easy creation of custom AI assistants and agents. The library provides tools for summarizing text, rephrasing text, legal tasks like summarizing legal text and critiquing as a judge, financial tasks like analyzing balance sheets and income statements, and database tools for inspecting and querying databases. It also supports observability via LlamaIndex and Arize Phoenix integration.

LLM-ollama is a plugin that provides access to models running on an Ollama server. It allows users to query the Ollama server for a list of models, register them with LLM, and use them for prompting, chatting, and embedding. The plugin supports image attachments, embeddings, JSON schemas, async models, model aliases, and model options. Users can interact with Ollama models through the plugin in a seamless and efficient manner.

horde-engine is a wrapper around ComfyUI designed to run inference pipelines visually designed in the ComfyUI GUI. It enables users to design inference pipelines in ComfyUI and then call them programmatically, maintaining compatibility with the existing horde implementation. The library provides features for processing Horde payloads, initializing the library, downloading and validating models, and generating images based on input data. It also includes custom nodes for preprocessing and tasks such as face restoration and QR code generation. The project depends on various open source projects and bundles some dependencies within the library itself. Users can design ComfyUI pipelines, convert them to the backend format, and run them using the run_image_pipeline() method in hordelib.comfy.Comfy(). The project is actively developed and tested using git, tox, and a specific model directory structure.

Godot LLM is a plugin that enables the utilization of large language models (LLM) for generating content in games. It provides functionality for text generation, text embedding, multimodal text generation, and vector database management within the Godot game engine. The plugin supports features like Retrieval Augmented Generation (RAG) and integrates llama.cpp-based functionalities for text generation, embedding, and multimodal capabilities. It offers support for various platforms and allows users to experiment with LLM models in their game development projects.

Garak is a free tool that checks if a Large Language Model (LLM) can be made to fail in a way that is undesirable. It probes for hallucination, data leakage, prompt injection, misinformation, toxicity generation, jailbreaks, and many other weaknesses. Garak's a free tool. We love developing it and are always interested in adding functionality to support applications.

Pieces CLI for Developers is a comprehensive command-line interface (CLI) tool designed to interact seamlessly with Pieces OS. It provides functionalities such as asset management, application interaction, and integration with various Pieces OS features. The tool is compatible with Windows 10 or greater, Mac, and Windows operating systems. Users can install the tool by running 'pip install pieces-cli' or 'brew install pieces-cli'. After installation, users can access the tool's functionalities through the terminal by using the 'pieces' command followed by subcommands and options. The tool supports various commands, which can be found in the documentation. Developers can contribute to the project by forking and cloning the repository, setting up a virtual environment, installing dependencies with poetry, and running test cases with pytest and coverage.

This tool utilizes the OpenAI ChatGPT API to translate text, with a focus on line-based translation, particularly for SRT subtitles. It optimizes token usage by removing SRT overhead and grouping text into batches, allowing for arbitrary length translations without excessive token consumption while maintaining a one-to-one match between line input and output.

Olah is a self-hosted lightweight Huggingface mirror service that implements mirroring feature for Huggingface resources at file block level, enhancing download speeds and saving bandwidth. It offers cache control policies and allows administrators to configure accessible repositories. Users can install Olah with pip or from source, set up the mirror site, and download models and datasets using huggingface-cli. Olah provides additional configurations through a configuration file for basic setup and accessibility restrictions. Future work includes implementing an administrator and user system, OOS backend support, and mirror update schedule task. Olah is released under the MIT License.

This repository provides an original implementation of Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications. It includes tools for neuron-level pruning, pruning based on set difference, Wanda/SNIP score dumping, rank-level pruning, and rank removal with orthogonal projection. Users can specify parameters like prune method, datasets, sparsity ratio, model, and save location to evaluate and modify neural networks for safety alignment.

Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment interfaces and libraries for understanding AI systems. It empowers developers and stakeholders to develop and monitor AI responsibly, enabling better data-driven actions. The toolbox includes visualization widgets for model assessment, error analysis, interpretability, fairness assessment, and mitigations library. It also offers a JupyterLab extension for managing machine learning experiments and a library for measuring gender bias in NLP datasets.

Fairlearn is a Python package designed to help developers assess and mitigate fairness issues in artificial intelligence (AI) systems. It provides mitigation algorithms and metrics for model assessment. Fairlearn focuses on two types of harms: allocation harms and quality-of-service harms. The package follows the group fairness approach, aiming to identify groups at risk of experiencing harms and ensuring comparable behavior across these groups. Fairlearn consists of metrics for assessing model impacts and algorithms for mitigating unfairness in various AI tasks under different fairness definitions.

OpenPromptInjection is an open-source toolkit for attacks and defenses in LLM-integrated applications, enabling easy implementation, evaluation, and extension of attacks, defenses, and LLMs. It supports various attack and defense strategies, including prompt injection, paraphrasing, retokenization, data prompt isolation, instructional prevention, sandwich prevention, perplexity-based detection, LLM-based detection, response-based detection, and know-answer detection. Users can create models, tasks, and apps to evaluate different scenarios. The toolkit currently supports PaLM2 and provides a demo for querying models with prompts. Users can also evaluate ASV for different scenarios by injecting tasks and querying models with attacked data prompts.

This repository contains slides, notebooks, and data for the Machine Learning University (MLU) Responsible AI class. The mission is to make Machine Learning accessible to everyone, covering widely used ML techniques and applying them to real-world problems. The class includes lectures, final projects, and interactive visuals to help users learn about Responsible AI and core ML concepts.

The AI Fairness 360 toolkit is an open-source library designed to detect and mitigate bias in machine learning models. It provides a comprehensive set of metrics, explanations, and algorithms for bias mitigation in various domains such as finance, healthcare, and education. The toolkit supports multiple bias mitigation algorithms and fairness metrics, and is available in both Python and R. Users can leverage the toolkit to ensure fairness in AI applications and contribute to its development for extensibility.

This repository is a collection of resources focused on interpretability in large language models (LLMs). It aims to help beginners get started in the area and keep researchers updated on the latest progress. It includes libraries, blogs, tutorials, forums, tools, programs, papers, and more related to interpretability in LLMs.

LLM Hallucination Index - RAG Special is a comprehensive evaluation of large language models (LLMs) focusing on context length and open vs. closed-source attributes. The index explores the impact of context length on model performance and tests the assumption that closed-source LLMs outperform open-source ones. It also investigates the effectiveness of prompting techniques like Chain-of-Note across different context lengths. The evaluation includes 22 models from various brands, analyzing major trends and declaring overall winners based on short, medium, and long context insights. Methodologies involve rigorous testing with different context lengths and prompting techniques to assess models' abilities in handling extensive texts and detecting hallucinations.

The 'llm-misinformation-survey' repository is dedicated to the survey on combating misinformation in the age of Large Language Models (LLMs). It explores the opportunities and challenges of utilizing LLMs to combat misinformation, providing insights into the history of combating misinformation, current efforts, and future outlook. The repository serves as a resource hub for the initiative 'LLMs Meet Misinformation' and welcomes contributions of relevant research papers and resources. The goal is to facilitate interdisciplinary efforts in combating LLM-generated misinformation and promoting the responsible use of LLMs in fighting misinformation.