fergusfettes Goto Github PK

beetimer

Simple timer for beeminder tasks.

boxkit

A blingier starting image for Toolbx and Distrobox.

command-line-loom

Command Line version of Loom, a creative writing tool for exploring the akashic records.

computersimulation

my holder for my computer simulation homeworks. mostly ising/potts model and a little bit of random walks so far. ill try and upload the stuff from last semester at some point

docker-apps

docker-devpi

Dockerfile for devpi pypi server

docker-nfs-server

A lightweight, robust, flexible, and containerized NFS server.

docker-web-server

development and production environments for threejs experiments

dotfiles

my dotfiles

eden_demo

simple eden model implementation

emily

Complete Poems of Emily Dickinson

fergusfettes.github.io

Personal site of Fergus Fettes

fergusfettes.github.io-archive

fieldshift

Fieldshift Dataset

flask-query-builder

A query builder for flask and sqlalchemy

gpt_definition_trees

code for generating "definition trees" for (not-necessarily-token) GPT-J embeddings

helicaseanalysis

Data Collection Software

hydra-patches

hyperdb

A hyper-fast local vector database for use with LLM Agents. Now accepting SAFEs at $35M cap.

javascript-playground

kronenzeitung

language processing on right wing austrian newspapers

langchain-1

⚡ Building applications with LLMs through composability ⚡

latent-cartography

lattice

Lattice Model Simulations

llama_index-1

LlamaIndex (GPT Index) is a project that provides a central interface to connect your LLM's with external data.

loom

Multiversal tree writing interface for human-AI collaboration

loveuiq

Trying to automatically convert the script of Deleuze and Guattaris A Love of UIQ into a radioplay

mayorofwhoville

Trying to learn about networking in docker swarms with websockets and asyncio, made a little game

mentat

Mentat - The AI Coding Assistant

minihf

MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user develop their prompts into full models.