My personal frontpage app

Prompt engineering, automated.

A benchmark to evaluate language models on questions I've previously asked them to solve.

My favorite C programming practices.

get structured objects from LLMs -- teaching implementation of the instructor library in python

An extremely fast Python package and project manager, written in Rust.

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

Neural Search

Minimalistic large language model 3D-parallelism training

OCR, layout analysis, reading order, table recognition in 90+ languages

LLM papers I'm reading, mostly on inference and model compression

Named tensors with first-class dimensions for PyTorch

GPU programming related news and material links

The full minitorch student suite.

Module 0 - Fundamentals

Math OCR model that outputs LaTeX and markdown

Robust recipes to align language models with human and AI preferences

Go ahead and axolotl questions

Examples in the MLX framework

MinT: Minimal Transformer Library and Tutorials

bert implementation in mlx -- throwback to NLP in 2018

MLX: An array framework for Apple silicon

mlx implementations of various transformers, speedups, training

Fine-tune mistral-7B on 3090s, a100s, h100s

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

minimal transformers/llms for search

build your own vector database -- the littlest hnsw

A comprehensive deep dive into the world of tokens

DSPy: The framework for programming—not prompting—foundation models