Chloe (ChloeL19)

ChloeL19

Geek Repo

Location:Hawaii/Cambridge

Github PK Tool:Github PK Tool

Chloe's repositories

DafnyBench

I'm really gonna translate HumanEval this time. Y'all haven't seen nothing yet.

Language:DafnyStargazers:4Issues:2Issues:0

cs181-s23-homeworks

Public homework assignments for Harvard's CS 181: Machine Learning (Spring 2023)

Language:TeXStargazers:1Issues:0Issues:0

RLVF

Reinforcement Learning from Verifier Feedback in Coq

Language:Jupyter NotebookStargazers:1Issues:3Issues:0

snake_rl

Building a reinforcement learning algorithm to solve the snake game

Language:PythonStargazers:0Issues:2Issues:0

BabySynth

A bottom-up synthesizer for two very small target languages.

Language:PythonStargazers:0Issues:0Issues:0

CanGPTBuildAWebsite-

The answer is no it cannot, but saving the attempt here anyway

Language:JavaScriptStargazers:0Issues:0Issues:0

circuit-breaker-experiments

Doing stuff with circuit broken models

Language:PklStargazers:0Issues:0Issues:0

circuit-breakers

Improving Alignment and Robustness with Circuit Breakers

Stargazers:0Issues:0Issues:0

CS124_P3

3rd programming assignment for CS124

Language:PythonStargazers:0Issues:1Issues:0

CS_BootCamps_LandingPage

Landing page for CS bootcamps program

Language:JavaScriptLicense:MITStargazers:0Issues:2Issues:0

dafny

Dafny is a verification-aware programming language

Language:C#License:NOASSERTIONStargazers:0Issues:0Issues:0

DiffusionTutorial

How diffusion works, socratic style, hopefully half as good as how Callum McDougal describes stuff

Language:PythonStargazers:0Issues:0Issues:0

discovering_latent_knowledge

Just messing around.

License:MITStargazers:0Issues:0Issues:0

elk

Keeping language models honest by directly eliciting knowledge encoded in their activations. Building on "Discovering latent knowledge in language models without supervision" (Burns et al. 2022)

License:MITStargazers:0Issues:0Issues:0
Language:PythonLicense:NOASSERTIONStargazers:0Issues:0Issues:0

InvokeAI

This version of Stable Diffusion features a slick WebGUI, an interactive command-line script that combines text2img and img2img functionality in a "dream bot" style interface, and multiple features and other enhancements. For more info, see the website link below.

Language:Jupyter NotebookLicense:NOASSERTIONStargazers:0Issues:0Issues:0

llm-verified-with-monte-carlo-tree-search

LLM verified with Monte Carlo Tree Search

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

open_spiel

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

Language:C++License:Apache-2.0Stargazers:0Issues:0Issues:0

pacman-react

A Pac Man game, built with React, TypeScript, MobX, styled-components, and Xstate

Language:TypeScriptStargazers:0Issues:0Issues:0

PacmanGym

Open AI Gym version of Berkeley AI Pacman with images as states

Language:PythonStargazers:0Issues:0Issues:0

PacmanWebappV01.0

For human testing of our noisy Pacman environment.

Language:TypeScriptStargazers:0Issues:1Issues:0

Programming2_124

Strassen's for the win!

Language:C++Stargazers:0Issues:2Issues:0

RLforPacman

Testing github CoPilot and creating RL agent for Pacman.

Language:PythonStargazers:0Issues:1Issues:0

SlipperCartpole

Cartpole on ice

Language:PythonStargazers:0Issues:1Issues:0

SlipperyCartpole

A toolkit for developing and comparing reinforcement learning algorithms.

Language:PythonLicense:NOASSERTIONStargazers:0Issues:0Issues:0

sourcing_app

Building an app for sourcing

Language:PythonStargazers:0Issues:2Issues:0

tracr-synthesis

Final project for CS252R

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:0Issues:0Issues:0
Language:PythonStargazers:0Issues:0Issues:0
Language:PythonStargazers:0Issues:0Issues:0