James M. Tucker's repositories
DATA_340_NLP
Natural Langauge Processing Course Syllabus for DATA 340
AskHuberman
This repo contains machine learning code that analyzes Andrew Huberman's public facing scientific education materials
awesome-hebrew-nlp
:book: A curated list of resources for NLP (Natural Language Processing) for Hebrew
course-nlp
A Code-First Introduction to NLP course
dotfiles
Default dotfiles and configuration options to setup a new machine
english_words
:memo: A text file containing 479k English words for all your dictionary/word-based projects e.g: auto-completion / autosuggestion
huggingface_notebooks
Notebooks using the Hugging Face libraries ๐ค
geoBoundaries
geoBoundaries : A Political Administrative Boundaries Dataset (www.geoboundaries.org)
NSF_Grants
Data and code to analyze National Science Foundation Grants
PDF_to_Text
An API to covert pdf to txt source files
plagiarism_publisher
A suite of AI tools to detect plagiarism and direct researchers to proper sources for attribution
pubmed-rct-expanded
PubMed 200k RCT dataset: a large dataset for sequential sentence classification.
Samba
Official implementation of "Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling"
TopicExplorer
NLP pipeline using word2vec (preprocessing/embedding/prediction/clustering)
user-dotbrev
Setup script for each Brev user. Used to add custom user settings in each new project (ex. terminal profiles, vscode settings).