Joe Barrow

commonforms. CommonForms — open models to auto-detect PDF form fields

LambdaNet. Purely functional artificial neural network library implemented in Haskell.

allennlp_tutorial. Tutorial on how to use AllenNLP for sequence modeling (including hierarchical LSTMs and CRF decoding)

tinyhnsw. build your own vector database -- the littlest hnsw

mlx-playground. mlx implementations of various transformers, speedups, training

srt-player. A jQuery plugin for playing SRT files with HTML5 video.

distillate. PDF Extraction Toolkit (wraps and trains LayoutLM)

capstone. Using Recurrent Neural Networks (RNN's) for music and language instruction.

pytorch-reading-group. A reading group/practicum focused on hands-on deep learning for NLP with PyTorch.

formalpdf. Python PDF Form Library: Extract, Fill, Create, Flatten

bert_from_scratch. Training BERT from scratch on a Cloud TPU

NeuroJet. The computational neuroscience simulation tool from Levy Labs.

reteach. Duolingo SLAM experiments, written in AllenNLP

minstructor. get structured objects from LLMs -- teaching implementation of the instructor library in python

multitask. PyTorch library for multitask learning.

checklists. A set of checklists to help with computer science research (NLP and Machine Learning in particular).

mlxbert. bert implementation in mlx -- throwback to NLP in 2018

mvlite. Fast, local multi-vector retrieval: supercharge RAG on your machine

pdfsplitter. Web app to split and merge PDFs, hosted on Modal

peppermint. minimal transformers/llms for search

rnn. playing with recurrent neural networks

CHip. A C implementation of a Hippocampus

gboggle. Genetic Algorithms for finding the best Boggle board given a dictionary.

jbarrow.github.io. Personal blog for Joe Barrow

awesome-machine-learning. A curated list of awesome Machine Learning frameworks, libraries and software.

mnemonic-reader. PDF reader/highlighter with spaced repetition flash cards