stockeh / mlx-grokkingLinks
Grokking on modular arithmetic in less than 150 epochs in MLX
☆14Updated 11 months ago
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
- PCCL (Prime Collective Communications Library) implements fault tolerant collective communications over IP☆131Updated last month
- SIMD quantization kernels☆87Updated last month
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆106Updated 7 months ago
- look how they massacred my boy☆63Updated last year
- Simple Transformer in Jax☆139Updated last year
- NanoGPT-speedrunning for the poor T4 enjoyers☆72Updated 5 months ago
- NanoGPT (124M) quality in 2.67B tokens☆28Updated last month
- H-Net Dynamic Hierarchical Architecture☆80Updated last month
- Approximating the joint distribution of language models via MCTS☆21Updated 11 months ago
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆18Updated 2 months ago
- Plotting (entropy, varentropy) for small LMs☆98Updated 4 months ago
- Entropy Based Sampling and Parallel CoT Decoding☆17Updated last year
- ☆40Updated last year
- Simple repository for training small reasoning models☆40Updated 8 months ago
- ☆12Updated last year
- Compiling useful links, papers, benchmarks, ideas, etc.☆45Updated 7 months ago
- Jax like function transformation engine but micro, microjax☆33Updated 11 months ago
- Solidity contracts for the decentralized Prime Network protocol☆27Updated 3 months ago
- NSA Triton Kernels written with GPT5 and Opus 4.1☆65Updated 2 months ago
- MLX port for xjdr's entropix sampler (mimics jax implementation)☆62Updated 11 months ago
- The Prime Intellect CLI provides a powerful command-line interface for managing GPU resources across various providers☆98Updated this week
- A tree-based prefix cache library that allows rapid creation of looms: hierarchal branching pathways of LLM generations.☆72Updated 8 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆55Updated 8 months ago
- The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…☆101Updated last week
- Lego for GRPO☆30Updated 4 months ago
- DeMo: Decoupled Momentum Optimization☆194Updated 10 months ago
- ☆45Updated 4 months ago
- aesthetic tensor visualiser☆27Updated 5 months ago