haraschax / nogradLinks
Gradient descent is cool and all, but what if we could delete it?
☆104Updated 3 months ago
Alternatives and similar repositories for nograd
Users that are interested in nograd are comparing it to the libraries listed below
Sorting:
- Simple Transformer in Jax☆139Updated last year
- look how they massacred my boy☆63Updated last year
- A graph visualization of attention☆57Updated 6 months ago
- ComplexTensor: Machine Learning By Bridging Classical and Quantum Computation☆79Updated last year
- The history files when recording human interaction while solving ARC tasks☆118Updated this week
- Plotting (entropy, varentropy) for small LMs☆99Updated 6 months ago
- ☆96Updated last year
- MLX port for xjdr's entropix sampler (mimics jax implementation)☆62Updated last year
- Following Karpathy with GPT-2 implementation and training, writing lots of comments cause I have memory of a goldfish☆172Updated last year
- SIMD quantization kernels☆93Updated 3 months ago
- papers.day☆91Updated last year
- 🌲 A 3D, interactive semantic graph of hacker interests at TreeHacks, scraped from Slack intro messages☆74Updated last year
- ☆129Updated 11 months ago
- i will automate factorio☆111Updated last year
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆108Updated 9 months ago
- ☆109Updated last year
- Solve puzzles to improve your tinygrad skills!☆164Updated last month
- noise_step: Training in 1.58b With No Gradient Memory☆221Updated 11 months ago
- A tree-based prefix cache library that allows rapid creation of looms: hierarchal branching pathways of LLM generations.☆76Updated 10 months ago
- could we make an ml stack in 100,000 lines of code?☆46Updated last year
- A package for defining deep learning models using categorical algebraic expressions.☆61Updated last year
- Reasoning Computers. Lambda Calculus, Fully Differentiable. Also Neural Stacks, Queues, Arrays, Lists, Trees, and Latches.☆283Updated last year
- Official CLI and Python SDK for Prime Intellect - access GPU compute, remote sandboxes, RL environments, and distributed training infrast…☆115Updated this week
- Just large language models. Hackable, with as little abstraction as possible. Done for my own purposes, feel free to rip.☆44Updated 2 years ago
- smol models are fun too☆92Updated last year
- a highly efficient compression algorithm for the n1 implant (neuralink's compression challenge)☆46Updated last year
- parallelized hyperdimensional tictactoe☆126Updated last year
- ☆89Updated last year
- Modify Entropy Based Sampling to work with Mac Silicon via MLX☆49Updated last year
- small auto-grad engine inspired from Karpathy's micrograd and PyTorch☆277Updated last year