ruanvdmerwe

ruanvdmerwe's Stars

• fastapi/fastapi

  FastAPI framework, high performance, easy to learn, fast to code, ready for production

  Language:Python79.2k6.8k

• pydantic/pydantic-ai

  Agent Framework / shim to use Pydantic with LLMs

  Language:Python4.9k330

• VikParuchuri/marker

  Convert PDF to markdown + JSON quickly with high accuracy

  Language:Python19.1k1.1k

• xu3kev/BARC

  Bootstrapping ARC

  Language:Python889

• microsoft/DeepSpeed

  DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

  Language:Python36.1k4.2k

• dottxt-ai/outlines

  Structured Text Generation

  Language:Python10.2k533

• ShishirPatil/gorilla

  Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

  Language:Python11.6k1k

• pytorch/ao

  PyTorch native quantization and sparsity for training and inference

  Language:Python1.7k191

• pytorch/torchtitan

  A PyTorch native library for large model training

  Language:Python2.9k233

• vllm-project/vllm

  A high-throughput and memory-efficient inference and serving engine for LLMs

  Language:Python33.2k5k

• huggingface/alignment-handbook

  Robust recipes to align language models with human and AI preferences

  Language:Python4.9k420

• linkedin/Liger-Kernel

  Efficient Triton Kernels for LLM Training

  Language:Python4.1k237

• lorenmt/clarity-template

  Clarity: A Minimalist Website Template for AI Research

  Language:CSS767

• huggingface/nanotron

  Minimalistic large language model 3D-parallelism training

  Language:Python1.4k135

• sympy/sympy

  A computer algebra system written in pure Python

  Language:Python13.2k4.5k

• Lightning-AI/litgpt

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

  Language:Python11.1k1.1k

• pytorch/torchtune

  PyTorch native post-training library

  Language:Python4.5k471

• Lightning-AI/lightning-thunder

  Make PyTorch models up to 40% faster! Thunder is a source to source compiler for PyTorch. It enables using different hardware executors at once; across one or thousands of GPUs.

  Language:Python1.3k84

• coleifer/peewee

  a small, expressive orm -- supports postgresql, mysql, sqlite and cockroachdb

  Language:Python11.3k1.4k

• huggingface/trl

  Train transformer language models with reinforcement learning.

  Language:Python10.5k1.4k

• charlax/engineering-management

  A collection of inspiring resources related to engineering management and tech leadership

  Language:Shell7.6k626

• charlax/professional-programming

  A collection of learning resources for curious software engineers

  Language:Python47.1k3.7k

• google-deepmind/alphageometry

  Language:Python4.2k480

• dvmazur/mixtral-offloading

  Run Mixtral-8x7B models in Colab or consumer desktops

  Language:Python2.3k226

• XueFuzhao/OpenMoE

  A family of open-sourced Mixture-of-Experts (MoE) Large Language Models

  Language:Python1.4k74

• mistralai/mistral-inference

  Official inference library for Mistral models

  Language:Jupyter Notebook9.8k871

• facebookresearch/Pearl

  A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.

  Language:Jupyter Notebook2.7k174

• Gryphe/MergeMonster

  An unsupervised model merging algorithm for Transformers-based language models.

  Language:Python1019

• Delgan/loguru

  Python logging made (stupidly) simple

  Language:Python20.4k709

• gnobitab/InstaFlow

  :zap: InstaFlow! One-Step Stable Diffusion with Rectified Flow (ICLR 2024)

  Language:Python1.2k41