jalammar

tantivy

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

trax

Trax — Deep Learning with Clear Code and Speed

skorch

A scikit-learn compatible neural network library that wraps PyTorch

captum

Model interpretability and understanding for PyTorch

deep-daze

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

Top2Vec

Top2Vec learns jointly embedded topic, document and word vectors.

checklist

Beyond Accuracy: Behavioral Testing of NLP models with CheckList

pydocstyle

docstring style checker

TransformerLens

A library for mechanistic interpretability of GPT-style language models

pynndescent

A Python nearest neighbor descent for approximate nearest neighbors

NL-Augmenter

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

svcca

lucent

Lucid library adapted for PyTorch

python-arabic-reshaper

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

camel_tools

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

tantivy-py

Python bindings for Tantivy

toy-ml-pipeline

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

amazon-sagemaker-architecting-for-ml

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

attention_flow

tokenizations

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

sandbox-conversant-lib

Conversational AI tooling & personas built on Cohere's LLMs

genome-spy

A visualization grammar and GPU-accelerated toolkit for genomic data

sandbox-grounded-qa

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

sandbox-toy-semantic-search

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

diagNNose

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

xai-benchmark

A Diagnostic Study of Explainability Techniques for Text Classification

rnn_agreement

Evaluating recurrent neural networks on predicting subject-verb agreement dependencies

sandbox-accelerating-chatbot-training

Leveraging Cohere's models to enable zero-shot routing

efficient-columnwise-correlation

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

svcca-gpu

GPU fork of Singular Value Canonical Correlation Analysis for Neural Nets