stewy33

model-alignment

Model Alignment is a python library from the PAIR team that enable users to create model prompts through user feedback instead of manual prompt writing and editing. The technique makes use of constitutional principles to align prompts to users' desired values.

mwp_ReFT

sacrebleu

Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons

dspy

DSPy: The framework for programming—not prompting—foundation models

earlyoom

earlyoom - Early OOM Daemon for Linux

icecream

🍦 Never use print() to debug again.

pyro

Deep universal probabilistic programming with Python and PyTorch

test

Measuring Massive Multitask Language Understanding | ICLR 2021

continue

⏩ Continue is the leading open-source AI code assistant. You can connect any models and any context to build custom autocomplete and chat experiences inside VS Code and JetBrains

POWERplay

overcooked_ai

A benchmark environment for fully cooperative human-AI performance.

automatic_prompt_engineer

bombsquad-remote-android

BombSquad Remote App for Android

ChatGPT-System-Prompts

This repository contains a collection of the best system prompts for ChatGPT, a conversational AI model developed by OpenAI. Star this repository to help us reach 5,000 stars!

safety-gymnasium

NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark

python-astar

Simple implementation of the a-star algorithm in Python 🌟

PySR

High-Performance Symbolic Regression in Python and Julia

pymc

Bayesian Modeling and Probabilistic Programming in Python

safe-grid-gym

A gym interface for AI safety gridworlds created in pycolab.

seals

Benchmark environments for reward modelling and imitation learning algorithms.

vscode-sftp

Super fast sftp/ftp extension for VS Code

openDogV3

cleanrl

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

imitation

Clean PyTorch implementations of imitation and reward learning algorithms

blenderpy

Blender as a python module with easy-install

Crowded-Valley---Results

This repository contains the results for the paper: "Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers"

rgd

Relativistic Gradient Descent optimization method.

FirstExplicitMethod-HDM

Implementation of Hamiltonian Descent Methods (First explicit method) with Python3

rich

Rich is a Python library for rich text and beautiful formatting in the terminal.

Grad_CAM_plus_plus

A generalized gradient-based CNN visualization technique