bpben

professional-programming

A collection of learning resources for curious software engineers

Probabilistic-Programming-and-Bayesian-Methods-for-Hackers

aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)

lectures

Oxford Deep NLP 2017 course

litgpt

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

stanford-cs-230-deep-learning

VIP cheatsheets for Stanford's CS 230 Deep Learning

Parsr

Transforms PDF, Documents and Images into Enriched Structured Data

marvin

✨ Build AI interfaces that spark joy

osmnx

OSMnx is a Python package to easily download, model, analyze, and visualize street networks and other geospatial features from OpenStreetMap.

llm-numbers

Numbers every LLM developer should know

Top2Vec

Top2Vec learns jointly embedded topic, document and word vectors.

awesome-sentence-embedding

A curated list of pretrained sentence and word embedding models

tabula-py

Simple wrapper of tabula-java: extract table from PDF into pandas DataFrame

ecco

Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, BERT, RoBERTA, T5, and T0).

pymc-resources

PyMC educational resources

nlp-library

curated collection of papers for the nlp practitioner 📖👩‍🔬

Local-LLM-Comparison-Colab-UI

Compare the performance of different LLM that can be deployed locally on consumer hardware. Run yourself with Colab WebUI.

wtte-rnn

WTTE-RNN a framework for churn and time to event prediction

transformers

A collection of resources to study Transformers in depth.

datamapplot

Creating beautiful plots of data maps

deeplearning.ai

snowstorm

Scalable SNOMED CT Terminology Server using Elasticsearch

spacy-udpipe

spaCy + UDPipe

crash-model

Build a crash prediction modeling application that leverages multiple data sources to generate a set of dynamic predictions we can use to identify potential trouble spots and direct timely safety interventions.

COVID-19

Gathering weather data in locations with confirmed COVID19 diagnoses. Confirmed diagnoses are from JHU data

data-inventories

A simple script to look for and process all the federal data.json data inventories.

Benchmarking_past_present_future

Workshop Home Page for Benchmarking: Past, Present and Future

word2vec

Word2Vec in Python, using Tensorflow.

geolocChina

Native Geolocation of Chinese Strings in R (no API keys required)

InformationDropout

pieces

tech infra components to assist with mutual aid projects