stockeh / mlx-grokking
Grokking on modular arithmetic in less than 150 epochs in MLX
☆12Updated 3 months ago
Alternatives and similar repositories for mlx-grokking:
Users that are interested in mlx-grokking are comparing it to the libraries listed below
- ☆27Updated 6 months ago
- A collection of optimizers for MLX☆29Updated this week
- Jax like function transformation engine but micro, microjax☆30Updated 3 months ago
- alternative way to calculating self attention☆18Updated 8 months ago
- Turing machines, Rule 110, and A::B reversal using Claude 3 Opus.☆59Updated 8 months ago
- ☆20Updated 2 months ago
- Simple Transformer in Jax☆130Updated 7 months ago
- ☆37Updated 6 months ago
- Alpha-Zero Connect Four NN trained via self play☆13Updated 4 months ago
- Modify Entropy Based Sampling to work with Mac Silicon via MLX☆49Updated 2 months ago
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆30Updated last month
- ☆13Updated last year
- Tensor library with autograd using only Rust's standard library☆64Updated 6 months ago
- A synthetic story narration dataset to study small audio LMs.☆31Updated last year
- Latent Program Network (from the "Searching Latent Program Spaces" paper)☆45Updated 2 months ago
- train entropix like a champ!☆19Updated 3 months ago
- direct preference optimization with only 1 model copy :)☆13Updated last year
- A repository of prompts and Python scripts for intelligent transformation of raw text into diverse formats.☆30Updated last year
- look how they massacred my boy☆63Updated 3 months ago
- MLX port for xjdr's entropix sampler (mimics jax implementation)☆62Updated 2 months ago
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆18Updated last week
- Schedule free optimiser implemented in JAX using Optimistix☆14Updated 8 months ago
- Extensive introductory writeup on Zig language functionalities☆10Updated 6 months ago
- Simplex Random Feature attention, in PyTorch☆72Updated last year
- NanoGPT (124M) quality in 2.67B tokens☆27Updated this week
- Eric's personal notes from NYSRG https://notes.ekzhang.com/events/nysrg☆14Updated 3 weeks ago
- Flexible, efficient, and context-aware generation from large unstructured knowledge sources.☆15Updated 8 months ago
- A package for defining deep learning models using categorical algebraic expressions.☆59Updated 6 months ago
- Modular Agentic AI Architecture - NousResearch x Teleport (Flashbots)☆53Updated 3 weeks ago
- Generative cellular automaton-like learning environments for RL.☆19Updated this week