proceduralia

proceduralia's Stars

• donnemartin/system-design-primer

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

  Language:Python260k6.7k28344.2k

• OpenInterpreter/open-interpreter

  A natural language interface for computers

  Language:Python49.5k3728644.3k

• charlax/professional-programming

  A collection of learning resources for curious software engineers

  Language:Python45.7k979273.6k

• mlabonne/llm-course

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

  Language:Jupyter Notebook32.8k342613.4k

• maybe-finance/maybe

  The OS for your personal finances

  Language:Ruby27.2k1412502.1k

• bloomberg/memray

  Memray is a memory profiler for Python

  Language:Python12.7k61170370

• stas00/ml-engineering

  Machine Learning Engineering Open Book

  Language:Python10.1k10318592

• TencentARC/PhotoMaker

  PhotoMaker

  Language:Jupyter Notebook8.5k98122665

• huggingface/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

  Language:Python7.2k1001.4k844

• eureka-research/Eureka

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

  Language:Jupyter Notebook2.7k2533241

• sgl-project/sglang

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

  Language:Python2.6k28260166

• webdataset/webdataset

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

  Language:Python2k21297154

• ysymyth/ReAct

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

  Language:Jupyter Notebook1.7k1627170

• google/maxtext

  A simple, performant and scalable Jax LLM!

  Language:Python1.3k2362229

• huggingface/nanotron

  Minimalistic large language model 3D-parallelism training

  Language:Python899415979

• mistralai/megablocks-public

  Language:Python8579051

• tatsu-lab/alpaca_farm

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

  Language:Python72784156

• ezelikman/quiet-star

  Code for Quiet-STaR

  Language:Python31011752

• RLHFlow/RLHF-Reward-Modeling

  Recipes to train reward model for RLHF.

  Language:Python28861018

• carlosferrazza/humanoid-bench

  Language:Python2697624

• allenai/reward-bench

  RewardBench: the first evaluation tool for reward models.

  Language:Python23844225

• facebookincubator/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.

  Language:C++180142033

• SalesforceAIResearch/DiffusionDPO

  Code for "Diffusion Model Alignment Using Direct Preference Optimization"

  Language:Python14161214

• YifeiZhou02/ArCHer

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

  Language:Python675910

• facebookresearch/RLCD

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

  Language:Python57733

• roeehendel/icl_task_vectors

  Language:Python491513

• facebookresearch/rlfh-gen-div

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

  Language:Python30432

• deeplearning-wisc/args

  Language:Python22343

• Jiuzhouh/Uncertainty-Aware-Language-Agent

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

  Language:Python13101

• spikedoanz/weenygrad

  Minimalist vector AD

  Language:Python9101