haraschax / nograd
Gradient descent is cool and all, but what if we could delete it?
☆102Updated last week
Related projects ⓘ
Alternatives and complementary repositories for nograd
- Simple Transformer in Jax☆119Updated 5 months ago
- ComplexTensor: Machine Learning By Bridging Classical and Quantum Computation☆73Updated this week
- i will automate factorio☆89Updated 3 months ago
- MLX port for xjdr's entropix sampler (mimics jax implementation)☆56Updated 2 weeks ago
- Reasoning Computers. Lambda Calculus, Fully Differentiable. Also Neural Stacks, Queues, Arrays, Lists, Trees, and Latches.☆235Updated 3 weeks ago
- Solve puzzles to improve your tinygrad skills!☆87Updated 2 months ago
- The history files when recording human interaction while solving ARC tasks☆95Updated this week
- look how they massacred my boy☆58Updated last month
- ☆95Updated last month
- small auto-grad engine inspired from Karpathy's micrograd and PyTorch☆179Updated this week
- 🌲 A 3D, interactive semantic graph of hacker interests at TreeHacks, scraped from Slack intro messages☆68Updated 6 months ago
- Following master Karpathy with GPT-2 implementation and training, writing lots of comments cause I have memory of a goldfish☆167Updated 3 months ago
- Tensor library with autograd using only Rust's standard library☆62Updated 4 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
- ☆99Updated 7 months ago
- ☆34Updated last week
- A really tiny autograd engine☆87Updated 7 months ago
- Modify Entropy Based Sampling to work with Mac Silicon via MLX☆49Updated 2 weeks ago
- papers.day☆79Updated 11 months ago
- Draw more samples☆180Updated 5 months ago
- parallelized hyperdimensional tictactoe☆110Updated 2 months ago
- A package for defining deep learning models using categorical algebraic expressions.☆56Updated 3 months ago
- A reinforcement learning framework based on MLX.☆220Updated 9 months ago
- smol models are fun too☆77Updated 2 weeks ago
- a highly efficient compression algorithm for the n1 implant (neuralink's compression challenge)☆45Updated 5 months ago
- Turing machines, Rule 110, and A::B reversal using Claude 3 Opus.☆60Updated 6 months ago
- Mistral7B playing DOOM☆122Updated 4 months ago
- a tiny vectorstore implementation built with numpy.☆56Updated 6 months ago
- ☆27Updated 4 months ago
- Entropy Based Sampling and Parallel CoT Decoding☆17Updated last month