stockeh / mlx-grokkingLinks
Grokking on modular arithmetic in less than 150 epochs in MLX
☆14Updated last year
Alternatives and similar repositories for mlx-grokking
Users that are interested in mlx-grokking are comparing it to the libraries listed below
Sorting:
- ☆28Updated last year
- train entropix like a champ!☆20Updated last year
- SIMD quantization kernels☆92Updated 2 months ago
- NSA Triton Kernels written with GPT5 and Opus 4.1☆65Updated 3 months ago
- Jax like function transformation engine but micro, microjax☆33Updated last year
- Simple Transformer in Jax☆139Updated last year
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆108Updated 8 months ago
- PCCL (Prime Collective Communications Library) implements fault tolerant collective communications over IP☆138Updated 2 months ago
- ☆45Updated 6 months ago
- H-Net Dynamic Hierarchical Architecture☆80Updated 2 months ago
- ☆13Updated last year
- NanoGPT-speedrunning for the poor T4 enjoyers☆73Updated 7 months ago
- minimal Energy-based transformer☆40Updated 3 weeks ago
- look how they massacred my boy☆63Updated last year
- ☆40Updated last year
- Entropy Based Sampling and Parallel CoT Decoding☆17Updated last year
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆18Updated 4 months ago
- NanoGPT (124M) quality in 2.67B tokens☆28Updated 2 months ago
- Solidity contracts for the decentralized Prime Network protocol☆27Updated 4 months ago
- Compiling useful links, papers, benchmarks, ideas, etc.☆45Updated 8 months ago
- DeMo: Decoupled Momentum Optimization☆197Updated 11 months ago
- ☆14Updated 7 months ago
- train with kittens!☆63Updated last year
- Simple repository for training small reasoning models☆46Updated 9 months ago
- Plotting (entropy, varentropy) for small LMs☆99Updated 6 months ago
- Approximating the joint distribution of language models via MCTS☆22Updated last year
- Modify Entropy Based Sampling to work with Mac Silicon via MLX☆49Updated last year
- Turing machines, Rule 110, and A::B reversal using Claude 3 Opus.☆58Updated last year
- Modded vLLM to run pipeline parallelism over public networks☆40Updated 6 months ago
- The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…☆112Updated last month