Pretrain, finetune, deploy 20+ LLMs on your own data. Uses state-of-the-art techniques: flash attention, FSDP, 4-bit, LoRA, and more.

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Together Mixture-Of-Agents (MoA) – 65.1% on AlpacaEval with OSS models

Portfolio analytics for quants, written in Python

David Attenborough narrates your life

Interact with your documents using the power of GPT, 100% privately, no data leaks

code for raspberry pico

Jøkul er et designsystem utviklet av Fremtind.

This repository contains Python One-liners codes to help you code like a pro!

CLI to quickly get a treemap visualization

Python wrapper for TA-Lib (http://ta-lib.org/).

fastquant — Backtest and optimize your ML trading strategies with only 3 lines of code!

My Portfolio

An open-source Python framework for hybrid quantum-classical machine learning.