haraschax / nograd
Gradient descent is cool and all, but what if we could delete it?
☆103Updated last month
Alternatives and similar repositories for nograd:
Users that are interested in nograd are comparing it to the libraries listed below
- Simple Transformer in Jax☆136Updated 7 months ago
- ☆98Updated 10 months ago
- look how they massacred my boy☆63Updated 4 months ago
- The history files when recording human interaction while solving ARC tasks☆97Updated this week
- could we make an ml stack in 100,000 lines of code?☆30Updated 7 months ago
- Just large language models. Hackable, with as little abstraction as possible. Done for my own purposes, feel free to rip.☆44Updated last year
- ComplexTensor: Machine Learning By Bridging Classical and Quantum Computation☆74Updated 3 months ago
- MLX port for xjdr's entropix sampler (mimics jax implementation)☆63Updated 3 months ago
- i will automate factorio☆99Updated 6 months ago
- Following master Karpathy with GPT-2 implementation and training, writing lots of comments cause I have memory of a goldfish☆167Updated 6 months ago
- Solve puzzles to improve your tinygrad skills!☆111Updated 5 months ago
- A really tiny autograd engine☆89Updated 10 months ago
- ☆96Updated 4 months ago
- papers.day☆92Updated last year
- a tiny vectorstore implementation built with numpy.☆60Updated 9 months ago
- A package for defining deep learning models using categorical algebraic expressions.☆59Updated 6 months ago
- ☆34Updated 7 months ago
- Mistral7B playing DOOM☆127Updated 7 months ago
- Reasoning Computers. Lambda Calculus, Fully Differentiable. Also Neural Stacks, Queues, Arrays, Lists, Trees, and Latches.☆246Updated 3 months ago
- small auto-grad engine inspired from Karpathy's micrograd and PyTorch☆248Updated 2 months ago
- parallelized hyperdimensional tictactoe☆112Updated 5 months ago
- ☆100Updated last month
- ☆36Updated 2 months ago
- An mlx project to train a base model on your whatsapp chats using (Q)Lora finetuning☆162Updated last year
- Tensor library with autograd using only Rust's standard library☆65Updated 7 months ago
- noise_step: Training in 1.58b With No Gradient Memory☆215Updated last month
- Learnings and programs related to CUDA☆262Updated this week
- Modify Entropy Based Sampling to work with Mac Silicon via MLX☆50Updated 3 months ago