RobertKirk
PhD student at @ucl-dark. Interested in understanding LLM fine-tuning, AI safety and (super)alignment.
@ucl-darkLondon
Pinned Repositories
minihack
MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research
rlfh-gen-div
This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity
dotfiles
A collection of personal scripts, aliases and the like from my personal software engineering practice
Graph-Comonads-from-Pebble-Games
Master Thesis code: Implementing Game Comonads in Finite Model Theory using Dependent Types in Idris
roam-solarized-theme
A strict solarized Roam Research theme
roam-tools
A small but growing collection of tools for Roam Research
stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
tinystories-wrappers
Code for the TinyStories experiments from "Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks".
tmux-ram
Plug and play RAM percentage and icon indicator for Tmux
RobertKirk's Repositories
RobertKirk/tinystories-wrappers
Code for the TinyStories experiments from "Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks".
RobertKirk/roam-tools
A small but growing collection of tools for Roam Research
RobertKirk/Graph-Comonads-from-Pebble-Games
Master Thesis code: Implementing Game Comonads in Finite Model Theory using Dependent Types in Idris
RobertKirk/dotfiles
A collection of personal scripts, aliases and the like from my personal software engineering practice
RobertKirk/roam-solarized-theme
A strict solarized Roam Research theme
RobertKirk/tmux-ram
Plug and play RAM percentage and icon indicator for Tmux
RobertKirk/client
🔥 A tool for visualizing and tracking your machine learning experiments. This repo contains the CLI and Python API.
RobertKirk/DeepRLAlgos
A collection of my own implementations of a variety of DeepRL Algorithms
RobertKirk/phasic-policy-gradient
Code for the paper "Phasic Policy Gradient"
RobertKirk/stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
RobertKirk/check_pdb_hook
Pre-commit hook to check for exposed PDB statements in Python files
RobertKirk/dmcontrol-generalization-benchmark
DMControl Generalization Benchmark
RobertKirk/dmenu
My personal dmenu fork
RobertKirk/dwm
My personal fork of dwm
RobertKirk/homebrew-neovim-nightly
Homebrew Cask tap for nightly neovim
RobertKirk/marge-bot
A merge-bot for GitLab
RobertKirk/nle
The NetHack Learning Environment
RobertKirk/rlfh-gen-div
This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity
RobertKirk/RobertKirk.github.io
personal blog
RobertKirk/RSSPlaylister
RobertKirk/scholar-alert-digest
Aggregate unread emails from Google Scholar alerts
RobertKirk/st
My fork of Simple terminal, with some patches and colours applied.
RobertKirk/surfingkeys-conf
A SurfingKeys configuration which adds 200+ key mappings for 17+ unique sites and OmniBar search suggestions for 45+ sites
RobertKirk/trlx
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
RobertKirk/voyager
🚀 Secure HAProxy Ingress Controller for Kubernetes
RobertKirk/weak-to-strong