Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️

Approximate Nearest Neighbor (ANN) search for high-dimensional data.

A lightweight benchmark for approximate nearest neighbor search

Benchmarks of approximate nearest neighbor libraries in Python

Unify Efficient Fine-Tuning of 100+ LLMs

Run upstream VS Code on a remote machine with access through a modern web browser from any device, anywhere.

GPT-2 small trained on phi-like data

Header-only C++/python library for fast approximate nearest neighbors

Universal LLM Deployment Engine with ML Compilation

Inference Llama 2 in one file of pure C

Tensor library for machine learning

Python bindings for llama.cpp

A demo project demonstrating how to read and write data into a Redis-backed state store using Kafka Streams.

Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

Recovering latent vectors from Generative Adversarial Networks

nannyml: post-deployment data science in python

[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821

Automatically Build Multiple ML Models with a Single Line of Code. Created by Ram Seshadri. Collaborators Welcome. Permission Granted upon Request.

Automatically Visualize any dataset, any size with a single line of code. Created by Ram Seshadri. Collaborators Welcome. Permission Granted upon Request.

Use advanced feature engineering strategies and select best features from your data set with a single line of code. Created by Ram Seshadri. Collaborators welcome.

Low-code tool for automating actions on real time data | Stream processing for the users.

A logical, reasonably standardized, but flexible project structure for doing and sharing data science work.

Minimalist project template for reproducible machine learning a la https://drivendata.github.io/cookiecutter-data-science/ and https://blog.mariokrapp.com/Cookiecutter_for_a_more_transparent_and_re…

Fancy stream processing made operationally mundane

Python Simple Object Storage - provides a list and dictionary interface that seamlessly stores data in a file, like a simplified database.

python partial dependence plot toolbox

🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models

A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning

semantically distinct key phrase extraction using hilbert hashes.