proceduralia

system-design-primer

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

open-interpreter

A natural language interface for computers

professional-programming

A collection of learning resources for curious software engineers

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

maybe

The OS for your personal finances

memray

Memray is a memory profiler for Python

ml-engineering

Machine Learning Engineering Open Book

PhotoMaker

PhotoMaker

accelerate

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

Eureka

Official Repository for "Eureka: Human-Level Reward Design via Coding Large Language Models" (ICLR 2024)

sglang

SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.

webdataset

A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

ReAct

[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models

megablocks-public

nanotron

Minimalistic large language model 3D-parallelism training

alpaca_farm

A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.

quiet-star

Code for Quiet-STaR

humanoid-bench

reward-bench

RewardBench: the first evaluation tool for reward models.

dynolog

Dynolog is a telemetry daemon for performance monitoring and tracing. It exports metrics from different components in the system like the linux kernel, CPU, disks, Intel PT, GPUs etc. Dynolog also integrates with pytorch and can trigger traces for distributed training applications.

RLHF-Reward-Modeling

A recipe to train reward models for RLHF.

SALMON

Self-Alignment with Principle-Following Reward Models

DiffusionDPO

Code for "Diffusion Model Alignment Using Direct Preference Optimization"

ArCHer

Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"

RLCD

Reproduction of "RLCD Reinforcement Learning from Contrast Distillation for Language Model Alignment

icl_task_vectors

rlfh-gen-div

This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity

args

Uncertainty-Aware-Language-Agent

This is the official repo for Towards Uncertainty-Aware Language Agent.

weenygrad

Minimalist vector AD