Alternatives and similar repositories for ml-by-hand

Users that are interested in ml-by-hand are comparing it to the libraries listed below

• kevinpdev / gpt-from-scratch
  Educational implementation of a small GPT model from scratch in a single Jupyter Notebook
  ☆96Updated 3 months ago
• saurabhaloneai / Llama-3-From-Scratch-In-Pure-Jax
  This repository contain the simple llama3 implementation in pure jax.
  ☆64Updated 3 months ago
• rodmarkun / SmolML
  A fully functional and simple Machine Learning library made entirely from scratch with Python.
  ☆279Updated last week
• idoh / mamba.np
  A pure NumPy implementation of Mamba.
  ☆223Updated 10 months ago
• ivanbelenky / RL
  R.L. methods and techniques.
  ☆191Updated 6 months ago
• tonio-m / python_neural_network
  🪝"mnist" in 60 lines of code, no dependencies. For educational purposes.
  ☆31Updated 11 months ago
• thomasahle / tensorgrad
  Machine Learning with Symbolic Tensors
  ☆278Updated last week
• kabir2505 / tiny-mixtral
  ☆39Updated last month
• bclarkson-code / Tricycle
  Autograd to GPT-2 completely from scratch
  ☆113Updated last month
• AniruddhaChattopadhyay / Books
  ☆162Updated 2 weeks ago
• telekinesis-inc / aiopandas
  Lightweight Pandas monkey-patch that adds async support to map, apply, applymap, aggregate, and transform, enabling seamless handling of …
  ☆127Updated 2 months ago
• dvgodoy / FineTuningLLMs
  Official repository of my book "A Hands-On Guide to Fine-Tuning LLMs with PyTorch and Hugging Face"
  ☆56Updated 2 months ago
• isaacperez / tinygpt
  A tiny version of GPT fully implemented in Python with zero dependencies
  ☆70Updated 5 months ago
• JUSTSUJAY / ML-Research-Papers
  ☆103Updated 9 months ago
• francoisfleuret / dlc
  ☆41Updated 5 months ago
• eduardoleao052 / Autograd-from-scratch
  Documented and Unit Tested educational Deep Learning framework with Autograd from scratch.
  ☆115Updated last year
• YuvrajSingh-mist / Paper-Replications
  A repository consisting of paper/architecture replications of classic/SOTA AI/ML papers in pytorch
  ☆196Updated last month
• canyon289 / GenAiGuidebook
  ☆73Updated 3 months ago
• kmohan321 / Research_Papers
  ☆46Updated 2 months ago
• moe18 / DeepMLeet
  ☆66Updated 11 months ago
• valine / training-hot-swap
  Pytorch script hot swap: Change code without unloading your LLM from VRAM
  ☆126Updated last month
• hkproj / multi-latent-attention
  ☆36Updated 2 weeks ago
• JINO-ROHIT / advanced_ml
  ☆46Updated 3 weeks ago
• tanishqkumar / beyond-nanogpt
  Minimal and annotated implementations of key ideas from modern deep learning research.
  ☆676Updated this week
• whitegra / dolphin
  An experimental transformer stack and symbolic computation engine built entirely from first principles in pure Python.
  ☆37Updated last month
• krupadav3 / Encoder-Block-in-CUDA
  Here's all my Python/Numba (CUDA) code for the encoder block I made :)
  ☆63Updated last month
• eugeneyan / llm-paper-notes
  Notes from the Latent Space paper club. Follow along or start your own!
  ☆234Updated 10 months ago
• Laz4rz / GPT-2
  Following master Karpathy with GPT-2 implementation and training, writing lots of comments cause I have memory of a goldfish
  ☆173Updated 10 months ago
• joennlae / tensorli
  Absolute minimalistic implementation of a GPT-like transformer using only numpy (<650 lines).
  ☆252Updated last year
• mlops-discord / dmls-bookclub
  ☆74Updated 11 months ago