mcognetta

LotteryTickets.jl

Sparsify Your Flux Models

mcognetta.github.io

ThreeHotKoreanModeling

A repo for parameter-efficient Korean character-level language modeling.

academic-budget-bert

Repository containing code for "How to Train BERT with an Academic Budget" paper

api

Lichess API documentation and examples

bar-hillel

ChainRulesCore.jl

AD-backend agnostic system defining custom forward and reverse mode rules. This is the light weight core to allow you to define rules for your functions in your packages, without depending on any particular AD system.

cpython

The Python programming language

dartchess

Dart chess library for native platforms

EsperantoWordSegmenter

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

fairseq2

FAIR Sequence Modeling Toolkit

Flux.jl

Relax! Flux is the ML library that doesn't make you tensor

Graphs.jl

An optimized graphs package for the Julia programming language

highway

Performance-portable, length-agnostic SIMD with runtime dispatch

joeynmt

Minimalist NMT for educational purposes

lichess-bot

A bridge between Lichess API and chess engines

llama2.c

Inference Llama 2 in one file of pure C

mcognetta

Metalhead.jl

Computer vision models for Flux

model-zoo

Please do not feed the models

networkx

Official NetworkX source code repository.

OpenFst.jl

Julia OpenFst interface

qwertle

sentencepiece

Unsupervised text tokenizer for Neural Network-based text generation.

SparseArrays.jl

SparseArrays.jl is a Julia stdlib

subword-nmt

Unsupervised Word Segmentation for Neural Machine Translation and Text Generation

tiny-diffusion

A minimal PyTorch implementation of probabilistic diffusion models for 2D datasets.

tinygrad

You like pytorch? You like micrograd? You love tinygrad! ❤️

tokenization-scorer

Simple-to-use scoring function for arbitrarily tokenized texts.