LLM101n: Let's build a Storyteller

Anthropic's Interactive Prompt Engineering Tutorial

Data processing with ML, LLM and Vision LLM

Open Source alternative to Algolia + Pinecone and an Easier-to-Use alternative to ElasticSearch ⚡ 🔍 ✨ Fast, typo tolerant, in-memory fuzzy Search Engine for building delightful search experiences

Inspect: A framework for large language model evaluations

A workbench application to test out different prompts on a variety of AI models to see how they perform

Unsloth Studio

Finetune Llama 4, DeepSeek-R1, Gemma 3 & Reasoning LLMs 2x faster with 70% less memory! 🦥

Marqo's Course on 'Fine-Tuning Embedding Models for Semantic Search'.

Generalised Contrastive Learning. This is a Repository for Google Shopping Dataset and Benchmarks followed by our novel fine-grained contrastive learning framework.

Unified embedding generation and search engine. Also available on cloud - cloud.marqo.ai

Tutorial for building LLM router

Repo for my Medium content, including Python and ML projects

A repository collecting model files for Neural Amp Modeler (NAM) all in one place

Automated testing and benchmarking for code generation agents.

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

Simple creation of data classes from dictionaries. Added ability to change field names, and get values from deep in the input dict.

WebChatGPT: A browser extension that augments your ChatGPT prompts with web results.

Short example for creating a correlation graph with Pandas and Gephi.

A scikit-learn-compatible library for estimating prediction intervals and controlling risks, based on conformal predictions.

Automated docker speedtest analyser tool with included web interface to monitor your internet speed connection over time. Setup at home on your NAS (Synology, QNAP tested) and the container runs ho…

GitHub Repo with various ML/AI/DS resources that I find useful

An open source python library for automated feature engineering

EvalML is an AutoML library written in python.

AI Code Completions

Web based interactive computing environment for H2O

Domain name classifier looking for good vs. possibly malicious providers

Apache Metron

H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K…