Peli de Halleux's starred repositories
transformers.js
State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!
mistral.rs
Blazingly fast LLM inference.
vscode-pull-request-github
GitHub Pull Requests for Visual Studio Code
graphrag-accelerator
One-click deploy of a Knowledge Graph powered RAG (GraphRAG) in Azure
augmentoolkit
Convert Compute And Books Into Instruct-Tuning Datasets (or classifiers)!
moatless-tools
We Have No Moat, And Neither Does Devin
prompt-api
A proposal for a web API for prompting browser-provided language models
do-not-answer
Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs
Open-Prompt-Injection
This repository provides implementation to formalize and benchmark Prompt Injection attacks and defenses
pint-benchmark
A benchmark for prompt injection detection systems.
language-models-on-the-command-line
Handout for a talk I gave about LLM and CLI tools
TaskTracker
TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a simple linear probe-based method and a more sophisticated metric learning method to achieve this. The project also releases the computationally expensive activation data to stimulate further AI safety research.
prompt-injection-mitigations
A collection of prompt injection mitigation techniques.