Pinned Repositories
allennlp-light
allennlp-light is a port of AllenNLP's core modules and nn portions into a standalone package with minimum dependencies
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, ... 🧠
bigram_embedder
da
domain_clusters
gumbel_softmax_text
multilingual-transformer
Regularized Neural Interlingua
true-detective
True Detective: Challenging Benchmark for Deep Abductive Reasoning in Foundation Models
xsim
Our Research in Cross-view Representational Similarity
Practicals
MaksymDel's Repositories
MaksymDel/allennlp-light
allennlp-light is a port of AllenNLP's core modules and nn portions into a standalone package with minimum dependencies
MaksymDel/xsim
Our Research in Cross-view Representational Similarity
MaksymDel/true-detective
True Detective: Challenging Benchmark for Deep Abductive Reasoning in Foundation Models
MaksymDel/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, ... 🧠
MaksymDel/toronto-csc321
My coursework of Toronto Intro to Neural Networks and Machine Learning (http://www.cs.toronto.edu/~rgrosse/courses/csc321_2018/)
MaksymDel/deep-reinforcement-learning-solutions
My solutions to the Deep Reinforcement Learning Nanodegree program
MaksymDel/domain_clusters
MaksymDel/allennlp-models
Officially supported AllenNLP models
MaksymDel/ARAE
Code for the paper "Adversarially Regularized Autoencoders (ICML 2018)" by Zhao, Kim, Zhang, Rush and LeCun
MaksymDel/ARENA_2.0
Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
MaksymDel/awesome-cto
A curated and opinionated list of resources for Chief Technology Officers, with the emphasis on startups
MaksymDel/Conference-Acceptance-Rate
Acceptance rates for the major AI conferences
MaksymDel/delmaksym.github.io
My personal webiste
MaksymDel/diplomacy_cicero
Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.
MaksymDel/expressive-resume
A beautiful resume/cover letter LaTeX template pair that are extraordinarily easy to use.
MaksymDel/firefox-translations-training
Training pipelines for Firefox Translations neural machine translation models
MaksymDel/huggingface-deep-rl-solutions
My solutions for the Huggingface's Deep Reinforcement Learning Course
MaksymDel/langchain
⚡ Building applications with LLMs through composability ⚡
MaksymDel/minimal
A Theme for GitHub Pages
MaksymDel/OpenPrompt
An Open-Source Framework for Prompt-Learning.
MaksymDel/phdati_template
University of Tartu PhD thesis template used by the Institute of Computer Science.
MaksymDel/python-project-template
Template repo for Python-based research projects
MaksymDel/RL4LMs
A modular RL library to fine-tune language models to human preferences
MaksymDel/sentence-transformers
Multilingual Sentence & Image Embeddings with BERT
MaksymDel/sherlock
Code, data, models for the Sherlock corpus
MaksymDel/smashed
Sequential MAppers for Sequences of HEterogeneous Dictionaries
MaksymDel/tinystories-wrappers
Code for the TinyStories experiments from "Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks".
MaksymDel/TransformerLens
A library for mechanistic interpretability of GPT-style language models
MaksymDel/trlx
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
MaksymDel/zero_shot_cot
Prod Env