Peli de Halleux (pelikhan)

pelikhan

Geek Repo

Company:Microsoft

Location:Seattle, WA

Home Page:https://aka.ms/jacdac

Twitter:@pelikhan

Github PK Tool:Github PK Tool


Organizations
lego-marshmallows
microsoft

Peli de Halleux's starred repositories

Language:PythonLicense:MITStargazers:614Issues:0Issues:0

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.

Language:Jupyter NotebookLicense:MITStargazers:16Issues:0Issues:0

tsx

⚡️ TypeScript Execute | The easiest way to run TypeScript in Node.js

Language:TypeScriptLicense:MITStargazers:8831Issues:0Issues:0

polars

Dataframes powered by a multithreaded, vectorized query engine, written in Rust

Language:RustLicense:NOASSERTIONStargazers:28222Issues:0Issues:0

graphrag

A modular graph-based Retrieval-Augmented Generation (RAG) system

Language:PythonLicense:MITStargazers:12823Issues:0Issues:0

litellm

Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate, Groq (100+ LLMs)

Language:PythonLicense:NOASSERTIONStargazers:10736Issues:0Issues:0

twoslash

Markup for generating rich type information in your documentations ahead of time.

Language:TypeScriptLicense:MITStargazers:443Issues:0Issues:0

Agentless

Agentless🐱: an agentless approach to automatically solve software development problems

Language:PythonLicense:MITStargazers:499Issues:0Issues:0

prompt-api

A proposal for a web API for prompting browser-provided language models

License:CC-BY-4.0Stargazers:163Issues:0Issues:0

maestro

A framework for Claude Opus to intelligently orchestrate subagents.

Language:PythonStargazers:3980Issues:0Issues:0

graphrag-accelerator

One-click deploy of a Knowledge Graph powered RAG (GraphRAG) in Azure

Language:PythonLicense:MITStargazers:1210Issues:0Issues:0

TOXIGEN

This repo contains the code for generating the ToxiGen dataset, published at ACL 2022.

Language:Jupyter NotebookLicense:NOASSERTIONStargazers:264Issues:0Issues:0

vscode-pull-request-github

GitHub Pull Requests for Visual Studio Code

Language:TypeScriptLicense:MITStargazers:2267Issues:0Issues:0

picopilot

GitHub Copilot in 70 lines of JavaScript

Language:JavaScriptLicense:MITStargazers:203Issues:0Issues:0

mistral.rs

Blazingly fast LLM inference.

Language:RustLicense:MITStargazers:3105Issues:0Issues:0

pint-benchmark

A benchmark for prompt injection detection systems.

Language:Jupyter NotebookLicense:MITStargazers:71Issues:0Issues:0

do-not-answer

Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:131Issues:0Issues:0

language-models-on-the-command-line

Handout for a talk I gave about LLM and CLI tools

Stargazers:55Issues:0Issues:0

moatless-tools

We Have No Moat, And Neither Does Devin

Language:PythonLicense:MITStargazers:169Issues:0Issues:0

transformers.js

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

Language:JavaScriptLicense:Apache-2.0Stargazers:10350Issues:0Issues:0

augmentoolkit

Convert Compute And Books Into Instruct-Tuning Datasets (or classifiers)!

Language:PythonLicense:MITStargazers:696Issues:0Issues:0

llama-fs

A self-organizing file system with llama 3

Language:Jupyter NotebookLicense:MITStargazers:4641Issues:0Issues:0

fabric

fabric is an open-source framework for augmenting humans using AI. It provides a modular framework for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.

Language:PythonLicense:MITStargazers:19695Issues:0Issues:0

astro

The web framework for content-driven websites. ⭐️ Star to support our work!

Language:TypeScriptLicense:NOASSERTIONStargazers:44441Issues:0Issues:0

vscode

VS Code extension for Vitest

Language:TypeScriptLicense:MITStargazers:729Issues:0Issues:0

BIPIA

A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.

Language:PythonLicense:NOASSERTIONStargazers:38Issues:0Issues:0

prompt-injection-mitigations

A collection of prompt injection mitigation techniques.

License:Apache-2.0Stargazers:15Issues:0Issues:0

HouYi

The automated prompt injection framework for LLM-integrated applications.

Language:PythonStargazers:149Issues:0Issues:0

Open-Prompt-Injection

This repository provides implementation to formalize and benchmark Prompt Injection attacks and defenses

Language:PythonStargazers:107Issues:0Issues:0

rebuff

LLM Prompt Injection Detector

Language:TypeScriptLicense:Apache-2.0Stargazers:1021Issues:0Issues:0