Maksym Del's repositories
allennlp-light
allennlp-light is a port of AllenNLP's core modules and nn portions into a standalone package with minimum dependencies
true-detective
True Detective: Challenging Benchmark for Deep Abductive Reasoning in Foundation Models
annotated_deep_learning_paper_implementations
🧑🏫 50! Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
toronto-csc321
My coursework of Toronto Intro to Neural Networks and Machine Learning (http://www.cs.toronto.edu/~rgrosse/courses/csc321_2018/)
allennlp-models
Officially supported AllenNLP models
ARENA_2.0
Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
awesome-cto
A curated and opinionated list of resources for Chief Technology Officers, with the emphasis on startups
biscuit
Single-page responsive Jekyll theme
delmaksym.github.io
My personal webiste
diplomacy_cicero
Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.
expressive-resume
A beautiful resume/cover letter LaTeX template pair that are extraordinarily easy to use.
langchain
⚡ Building applications with LLMs through composability ⚡
minimal
A Theme for GitHub Pages
OpenPrompt
An Open-Source Framework for Prompt-Learning.
phdati_template
University of Tartu PhD thesis template used by the Institute of Computer Science.
python-project-template
Template repo for Python-based research projects
RL4LMs
A modular RL library to fine-tune language models to human preferences
sentence-transformers
Multilingual Sentence & Image Embeddings with BERT
sherlock
Code, data, models for the Sherlock corpus
sidey
Sidey is a simple and minimalistic jekyll blogging theme.
smashed
Sequential MAppers for Sequences of HEterogeneous Dictionaries
tinystories-wrappers
Code for the TinyStories experiments from "Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks".
TransformerLens
A library for mechanistic interpretability of GPT-style language models
trlx
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
zero_shot_cot
Prod Env