streamline the fine-tuning process for multimodal models: PaliGemma, Florence-2, and Qwen2-VL

Fully open reproduction of DeepSeek-R1

Comparing M2M and mT5 on a rare language pairs, blog post: https://medium.com/@abdessalemboukil/comparing-facebooks-m2m-to-mt5-in-low-resources-translation-english-yoruba-ef56624d2b75

Find the accurate location of your devices

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

A beginner's project on automating the training, evaluation, versioning, and deployment of models using GitHub Actions.

Learn how to create, develop, and maintain a state-of-the-art MLOps code base

Parse files for optimal RAG

Must-have resource for anyone who wants to experiment with and build on the OpenAI vision API 🔥

YouTube

FastAPI framework, high performance, easy to learn, fast to code, ready for production

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and…

Batch data processing on the dockerized Hadoop cluster

The gateway component to make Spark on K8s much easier for Spark users.

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

In this project, we develop a machine-learning model for air-quality prediction in Poland

Effect of News Article on Stock Market Price implementing Sentiment Analysis

[Not Actively Maintained] Whitebox is an open source E2E ML monitoring platform with edge capabilities that plays nicely with kubernetes

The Demo for Blog: Modularization using Python and Docker (MicroService)

Building Big Data Pipelines with Apache Beam, published by Packt

Open-source repository for the ramp (Replicable AI for MicroPlanning) project

Predict stock market prices using RNN model with multilayer LSTM cells + optional multi-stock embeddings.

Use unsupervised and supervised learning to predict stocks

Stock market analyzer and predictor using Elasticsearch, Twitter, News headlines and Python natural language processing and sentiment analysis

Build vector tilesets from large collections of GeoJSON features.

AGI's query engine - Platform for building AI that can learn and answer questions over federated data.

Green Energy is an open source pure sine wave solar inverter.

Quadcopter with multibody, electrical and thermal models follows a path to deliver a package.

Machine Learning – Supervised Learning