- Michigan
- http://jeffq.com
- @theemozilla
Stars
Exploring finetuning public checkpoints on filter 8K sequences on Pile
LlamaIndex is the leading framework for building LLM-powered agents over your data.
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch
🥤🧑🏻🚀Code and dataset for our EMNLP 2023 paper - "SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization"
Mac OS X cross toolchain for Linux, FreeBSD, OpenBSD and Android (Termux)
A lightweight, dependency-free library for binding Lua to C++
A brief computer graphics / rendering course