Research Tools: code, datasets, & models

SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery [PyTorch implementation, dataset and pretrained models for the paper “SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery”]

OPPerTune is a framework that enables configuration tuning of applications, including those in live deployment. It reduces application interruptions while maximizing the performance of the application as and when the workload or the underlying infrastructure…

PwR Studio converts natural language (NL) instructions into robust code. Programming with Representations (PwR, pronounced “power”) is a software development approach that relies on a domain-specific language (DSL), or representation, defined by a developer specializing in…

Root repository for Plurality: The Future of Collaborative Technology and Democracy by E. Glen Weyl, Audrey Tang and the Plurality Community

“Parrot: Efficient Serving of LLM-based Applications with Semantic Variable” Parrot is a distributed serving system for LLM-based Applications. The Parrot API w/ Semantic Variable is served by a centralized cluster manager called ServeCore, which manages…

Scripting environment with convenient tooling for file ingestion, prompt development and structured data extraction.

This repo contains the code described in LLMR (opens in new tab), implementing the Large Language Model for Mixed Reality framework. This package serves as a prototype for “Speaking the world into existence”, which allows the…

promptbase is an evolving collection of resources, best practices, and example scripts for eliciting the best performance from foundation models like GPT-4. We currently host scripts demonstrating the Medprompt methodology, including examples of how we…

The phi-2 is a language model with 2.7 billion parameters. The phi-2 model was trained using the same data sources as phi-1, augmented with a new data source that consists of various NLP synthetic texts…

The language model phi-1.5 is a Transformer with 1.3 billion parameters. It was trained using the same data sources as phi-1, augmented with a new data source that consists of various NLP synthetic texts. When…