Sign in

Search and AI @Keenious, builder of things.

Building a scalable Knowledge Graph search for 60+ million academic papers with Weaviate vector search

Keenious is a search engine designed for students, researchers, and the curious! Our add-on app works directly from your text editor; analyzing your entire document and finding highly relevant results as you work. …

Model explanations for any transformer model in 2 lines.

Photo by Emily Morter on Unsplash

TL:DR: Transformers Interpret brings explainable AI to the transformers package with just 2 lines of code. It allows you to get word attributions and visualizations for those attributions simply. Right now the package supports all transformer models with a sequence classification head.

Check out the project here: https://github.com/cdpierse/transformers-interpret

Introduction

Model explainability…

Introducing Pyinfer a model agnostic tool for ML developers and researchers to benchmark inference statistics for models

Photo by CHUTTERSNAP on Unsplash

Find pyinfer on Github : https://github.com/cdpierse/pyinfer

Docs can be found here: https://pyinfer.readthedocs.io/en/latest/

Introduction

When developing machine learning models initial efforts are often put on measuring metrics that reflect how well a model performs for a given task.

This step is of course crucially important but when moving a model to production…

How to build a lightweight service for keyword extraction and fuzzy word matching in python.

Photo by WORKSITE Ltd. on Unsplash

Often when dealing with long sequences of text you’ll want to break those sequences up and extract individual keywords to perform a search, or query a database.

If the input text is natural language you most likely don’t want to query your database with every single word — instead, you…

Photo by Luca Onniboni on Unsplash

Natural Language Processing

Fine-tuning GPT-2 to be a screenwriter using Hugging Face’s transformers package.

Introduction

Over the past 2 years NLP and language generation have experienced a renaissance moment. With the onset of the transformer neural network architecture there has been an explosion of work (and hype) around the plethora of potential use cases for these types of models.

Language generation is a feature of…

How I built a multi model fight predictor using Scrapy, Deep Learning, Flask, and React.

Photo by dylan nolte on Unsplash

TL;DR: check out the predictor for yourself and see how it performs for an upcoming UFC fight card or check out the code on github

Project Overview

As a fan of MMA I often find myself trying to predict the outcome of fights on an upcoming fight card. The problem is that…

Charles Pierse

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store