Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.

Conversational AI tooling & personas built on Cohere's LLMs

A demonstration of how a toy (but usable!) semantic search engine can be quickly built using Cohere's platform.

A sandbox repo for grounded question answering with Cohere and Google Search

Lucid library adapted for PyTorch

A library for mechanistic interpretability of GPT-style language models

Python bindings for Tantivy

Tantivy is a full-text search engine library inspired by Apache Lucene and written in Rust

A Python nearest neighbor descent for approximate nearest neighbors

NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations

A scikit-learn compatible neural network library that wraps PyTorch

Simple command line tool for text to image generation using OpenAI's CLIP and Siren (Implicit neural representation network). Technique was originally created by https://twitter.com/advadnoun

A visualization grammar and GPU-accelerated toolkit for genomic data

Toy example of an applied ML pipeline for me to experiment with MLOps tools.

Top2Vec learns jointly embedded topic, document and word vectors.

GPU fork of Singular Value Canonical Correlation Analysis for Neural Nets

Efficient ways to compute Pearson's correlation between columns of two matrices in various scientific computing languages

A suite of Arabic natural language processing tools developed by the CAMeL Lab at New York University Abu Dhabi.

diagNNose is a Python library that facilitates a broad set of tools for analysing hidden activations of neural models.

Reconstruct Arabic sentences to be used in applications that don't support Arabic

Evaluating recurrent neural networks on predicting subject-verb agreement dependencies

docstring style checker

A Diagnostic Study of Explainability Techniques for Text Classification

Materials for a 2-day instructor led course on applying machine learning

Model interpretability and understanding for PyTorch

Robust and Fast tokenizations alignment library for Rust and Python https://tamuhey.github.io/tokenizations/

Beyond Accuracy: Behavioral Testing of NLP models with CheckList

Trax — Deep Learning with Clear Code and Speed