hamelsmu

system-design-primer

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

guidance

A guidance language for controlling large language models.

ml-engineering

Machine Learning Engineering Open Book

llama-recipes

Scripts for fine-tuning Llama2 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization & question answering. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment.Demo apps to showcase Llama2 for WhatsApp & Messenger

axolotl

Go ahead and axolotl questions

tree-of-thought-llm

[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models

jsonformer

A Bulletproof Way to Generate Structured JSON from Language Models

jupyter-ai

A generative AI extension for JupyterLab

agenta

The all-in-one LLM developer platform: prompt management, evaluation, human feedback, and deployment all in one place.

ghtop

See what's happening on GitHub in real time (also helpful if you need to use up your API quota as quickly as possible)

dbt-duckdb

dbt (http://getdbt.com) adapter for DuckDB (http://duckdb.org)

bulk

A Simple Bulk Labelling Tool

cog-llama-template

LLaMA Cog template

heroku-buildpack-nginx

Run NGINX in a Heroku app

dinghy

A GitHub activity digest tool

quartodoc

Generate API documentation with quarto

pget

parallel fetch

oauth-tutorial

Like GitHub Pages, but you choose who can see it without usernames & passwords.

chatstream

Example Shiny for Python app which talks to the OpenAI API

optimi

Fast, Modern, Memory Efficient, and Low Precision PyTorch Optimizers

metaflow-tools

Tools and utilities for operating Metaflow in production

peft-codegen-25

titan-sf

titan: a package manager for Snowflake DB

oauth-render-quarto

k8s-slackbot-python

Native K8s Slackbot with Python

fastai-reimplemented

Taking (most of) the exact codebase and reimplementing it based on my own ideas of good programming and literate practices

science_read

Text to speach for scientific papers

nyacomp

load pytorch tensors really fast with compression and memory reuse

wandb_create_report_action

codone

Codon optimization tool