Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

Code for the SIGDial 2021 paper: Schema-Guided Paradigm for Zero-Shot Dialog

Hikaru and GothamChess remind you when you have spent too much time thinking on a move.

DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue

[ICLR 2020] Learning to Move with Affordance Maps 🗺️🤖💨

Transformer implementation in PyTorch.

Code for SIGDial 2019 Best Paper: Structured Fusion Networks for Dialog https://arxiv.org/abs/1907.10016

A react-based UI interface for reply annotations in multiparticipant chats.

A Telegram bot that will simulate the messages of a specific user (both content and style)

Telegram Bot (All Purpose & Plugin Based)

Umple: Model-Oriented Programming - embed models in code and vice versa and generate complete systems

Android game where two players chase each other around the map.