A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.

Code and data for the paper: Learning Action and Reasoning-Centric Image Editing from Videos and Simulation

LlamaIndex is a data framework for your LLM applications

A conda-smithy repository for bm25s.

Joplin - the secure note taking and to-do app with synchronisation capabilities for Windows, macOS, Linux, Android and iOS.

AI-powered Jupyter Notebook — use local AI to generate and edit code cells, automatically fix errors, and chat with your data

Full text search in your Pandas dataframe

AndroidWorld is an environment and benchmark for autonomous agents

A large-scale information-rich web dataset, featuring millions of real clicked query-document labels

Llama-3 agents that can browse the web by following instructions and talking to you

Code for "Universal Adversarial Triggers Are Not Universal."

BrowserGym, a gym environment for web task automation in the Chromium browser.

The official Meta Llama 3 GitHub site

Code for "Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model", EMNLP Findings 2023

Code and data for reproducing baselines for TopiOCQA, an open-domain conversational question-answering dataset

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

Benchmarks, environments, and toolkits for general computer agents

GlotLID: Language Identification with Support for More Than 2000 Labels -- EMNLP 2023

A simple template to get started with pyodide inside React

Example using react and hooks inside pyodide with pure Python code. Based on: https://alpha.iodide.io/notebooks/420/

Chat UI for locally-hosted LLaMA-2

Helps you manage python libraries and environments

A collection of functions to help you easily train and run Tensorflow Keras. It includes 1-line auto-TPU support, GPU memory management, and tf.data builders.

React app for client-side image resizing, powered by Pillow+Pyodide

A collection of COVID-19 question-answer pairs and transformer baselines for evaluating QA models (Official Repository)