Test deployment of Cisco security LLM model on sagemaker

Automated web vulnerability scanning with LLM agents

Scrapy, a fast high-level web crawling & scraping framework for Python.

A new algorithm that formulates jailbreaking as a reasoning problem.

distributed trainer for LLMs

Adversary Emulation Framework

A high-throughput and memory-efficient inference and serving engine for LLMs

A small plugin for Xournal++ version 1.1.x and 1.2.x with vi-like modes

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

Inference code for LLaMA models in JAX

Alternative keyboard layouts featuring useful characters

A self-organizing file system with llama 3

Conversations between LLMs

The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.

Find, Filter, Preview, Pick. All lua, all the time.

Gemini to API : ) (Don't need API KEY) (ChatGPT, Claude, DeeepSeek, Grok and more)

TAP: An automated jailbreaking method for black-box LLMs

Space Saving algorithm implementation (StreamSummary) in Java, used to solve heavy hitters / topk items.

⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs

A code-searching tool similar to ack, but faster.

Minimal library to train LLMs on TPU in JAX with pjit().

LogAI - An open-source library for log analytics and intelligence

very currency

CodeGen is a family of open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.

Implementation of Perceiver, General Perception with Iterative Attention, in Pytorch