PurpleLlama
AI safety toolkit
A set of tools to help developers build responsibly with open generative AI models.
Set of tools to assess and improve LLM security.
3k stars
48 watching
450 forks
Language: Python
last commit: 23 days ago
Linked from 1 awesome list
corca-ai/awesome-llm-securityRelated projects:
| Repository | Description | Stars |
|---|---|---|
| meta-llama/llama-stack | Provides a set of standardized APIs and tools to build generative AI applications | 4,591 |
| meta-llama/llama3 | Provides pre-trained and instruction-tuned Llama 3 language models and tools for loading and running inference | 27,138 |
| meta-llama/llama | A collection of tools and utilities for deploying, fine-tuning, and utilizing large language models. | 56,437 |
 lightning-ai/lit-llama | An implementation of a large language model using the nanoGPT architecture | 5,993 |
 hiyouga/llama-factory | A unified platform for fine-tuning multiple large language models with various training approaches and methods | 34,436 |
 protectai/llm-guard | A security toolkit designed to protect interactions with large language models from various threats and vulnerabilities. | 1,242 |
| meta-llama/codellama | Provides inference code and tools for fine-tuning large language models, specifically designed for code generation tasks | 16,039 |
 alpha-vllm/llama2-accessory | An open-source toolkit for pretraining and fine-tuning large language models | 2,722 |
 opengvlab/llama-adapter | An implementation of a method for fine-tuning language models to follow instructions with high efficiency and accuracy | 5,754 |
 ggerganov/llama.cpp | Enables efficient inference of large language models using optimized C/C++ implementations and various backend frameworks | 68,190 |
 confident-ai/deepeval | A framework for evaluating large language models | 3,669 |
 trusted-ai/adversarial-robustness-toolbox | A Python library that provides tools and techniques to defend against various attacks on machine learning models and applications. | 4,878 |
 opennhp/opennhp | A Zero Trust networking protocol to hide servers and data from attackers by utilizing cryptography at the OSI 5th layer. | 13,515 |
 safellama/plexiglass | A toolkit to detect and protect against vulnerabilities in Large Language Models. | 121 |
 theodo-group/llphant | A comprehensive PHP framework for building generative AI applications using OpenAI GPT 4 and other LLMs. | 871 |