dvruette Goto Github PK

algorithmic-efficiency

MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvements in both training algorithms and models.

amivapi

The REST API behind most of AMIV's web services.

aurora

barrel-rec-pytorch

cat-website

concept-guidance

Code accompanying the paper "A Language Model's Guide Through Latent Space". It contains functionality for training and using concept vectors that control the behavior of LLMs at inference time.

courserevieweth

Code for forum to review courses at ETH

django-webpack-loader

Transparently use webpack with django

django-webpack-starter

exercise-collector

A tool that collects exercises from various lecture-websites and compiles them into a to-do list.

figaro

Source code for "FIGARO: Generating Symbolic Music with Fine-Grained Artistic Control"

figaro-survey

figaro-v2

firstunity

flash-attention

Fast and memory-efficient exact attention

gatsby-starter-netlify-cms

lion-pytorch

🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch

litellm

Call all LLM APIs using the OpenAI format. Use Azure, OpenAI, Cohere, Anthropic, Ollama, VLLM, Sagemaker, HuggingFace, Replicate (100+ LLMs)

lm-evaluation-harness

A framework for few-shot evaluation of autoregressive language models.

locoprop-torch

LocoProp implementation in PyTorch. (https://proceedings.mlr.press/v151/amid22a/amid22a.pdf)

ma_landschaft

merge-stable-diffusion-models-without-distortion

musemorphose

PyTorch implementation of MuseMorphose, a Transformer-based model for music style transfer.

neat-p5

Evolution simulation using p5.js and NEAT

netlify-cms-test

nuxt-global-components-bug

Showcases a bug where Nuxt fails to load global components if there is a node_modules with Nuxt installed next to the buildDir specified in the config.

open-assistant

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

pokemon-emerald-experiments

Playing Pokemon Red with Reinforcement Learning

pwa

pygba

A Python wrapper around the Game Boy Advance emulator mGBA with built-in support for gymnasium environments.