evelynmitchell Goto Github PK

shacl-playground

Implementation of a fully client-side SHACL validation playground. Supports a wide variety of RDF serializations.

sicp-pset-database

Archive of problem set database from the SICP course taught at MIT from 1981 to 1989.

sigmasep

Code for UAI 2018 paper by Forré & Mooij (causal discovery with mSCMs using sigma-separation)

simmer

Discrete Event Simulation for R

simplified_transformers

situational-awareness-evals

Measuring the situational awareness of language models

sktime

A unified framework for machine learning with time series

sleeper-agents-paper

Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".

smartpredictthenoptimize

Code for the paper "Smart 'Predict, then Optimize'"

smol-podcaster

smol-podcaster is your autonomous podcast production intern 🐣

smoldeveloper

with 100k context windows on the way, it's now feasible for every dev to have their own smol developer

smtrat

sof-elk

Configuration files for the SOF-ELK VM, used in SANS FOR572

softlearning

Softlearning is a reinforcement learning framework for training maximum entropy policies in continuous domains. Includes the official implementation of the Soft Actor-Critic algorithm.

sophia

Plug in and Play New optimizer that is 2x faster than Adam on LLMs. Effortless plugin and play to cut model training costs by 50%

sophia1

The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”

sourcegraph

Code Intelligence Platform

spacetime

Code for SpaceTime 🌌⏱️. Proposed in Effectively Modeling Time Series with Simple Discrete State Spaces, ICLR 2023.

sparseprimingrepresentations

Public repo to document some SPR stuff

spatially-embedded-rnn

Repository for example implementation of spatially-embedded RNNs. See https://www.jachterberg.com/seRNN for more information.

specfy

Open source Stack Intelligence Platform

spelltest

AI-to-AI Testing | Simulation framework for LLM-based applications

spiffworkflow

A powerful workflow engine implemented in pure Python

spin

The official implementation of Self-Play Fine-Tuning (SPIN)

src

stable-alignment

Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Language Models in Simulated Human Society".

stable-baselines3

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

stable-baselines3-contrib

Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code

stable-diffusion-webui

Stable Diffusion web UI

stablecascade