AI Developer Tool · Python

mamba-view

Rick@JuiceB0xC0de · Atlas 73.3 · #2= builder

What it is

This repository provides a RunPod-compatible wrapper for the Modal six-camera trainer of the Mamba-3 443M model, including the training script and a suite of observer tools (cameras) to capture detailed training dynamics such as embedding updates, layer transactions, memory paths, optimizer delivery, and pressure metrics.

Scored from the code at its last scan, 22 Oct 2026. How merit is scored

Where it counts

Machine Learning90%
NLP & LLMs60%
MLOps30%

How much of the project is about each field, as scoring counts it. It ranks in the field it is most about.

Around it on the Machine Learning board

Whole board

RankProjectBuilderFieldMerit

06, shared rankmines-smLibrary / Framework · RustThis repository provides a deterministic, no_std Minesweeper game engine implemented in Rust, designed as a reinforcement learning environment. It offers a bitboard-based state machine with observation and action mask tensors for neural network input, along with comprehensive…64.6/100AdvancedJarad PeckenpaughMachine Learning
08ocr-livive-netEducational Implementation · JavaScriptThis repository implements four machine learning classifiers (Centroid, k-NN, Perceptron, and a hand-written MLP) from scratch in Rust for browser-based OCR via WebAssembly, emphasizing transparency and zero dependencies. It includes data preparation scripts, training and…63.4/100AdvancedJarad PeckenpaughMachine Learning
09, shared rankResNet_Family-from-scratchArchitecture Reimplementation · Jupyter NotebookThis repository provides a from-scratch reimplementation of the ResNet family (ResNet-12, ResNet-18, ResNet-34, ResNet-50) in PyTorch, with manual implementations of BatchNorm and activation functions for educational purposes, including training and evaluation on CIFAR100.62.2/100AdvancedPop AlexandruMachine Learning
09, shared rankmamba-viewAI Developer Tool · Python62.2/100AdvancedRickMachine Learning
11, shared ranksilico-e4b-sae-runML Application · PythonThe repository trains a 42-layer JumpReLU Sparse Autoencoder (SAE) atlas for the Gemma 4 E4B language model using the E2B recipe and an event-aware trainer with automatic sparsity control. It generates a private Hugging Face dataset containing the SAEs and includes scripts for…62.0/100AdvancedRickMachine Learning

What it is

Where it counts

Around it on the Machine Learning board

More from Rick