Distributed data parallel support for torch-rb

State-of-the-art transformers for Ruby

Data manipulation and transformation for audio signal processing

Deep learning recommendation systems for Ruby

Data loaders and abstractions for text and NLP

Computer vision datasets, transforms, and models for Ruby

A Ruby-native interface for fine-tuning machine learning models, starting with image classification using SigLIP2

Denoises audio (Speech Enhancement) using GTCRN model

A minimal, hackable LLM implementation with inference capabilities. Port of Karpathy's nanochat.

Train and run GPT models in Ruby using torch.rb. A minimal, educational implementation of GPT-2 style models.

Rumale::Torch provides the learning and inference by the neural network defined in torch.rb with the same interface as Rumale

Seq2seq transformer for transliteration in Ruby.

A seq2seq transformer suited for transliteration. Written in Ruby. Includes packages for training models

Composable data loading for Ruby

DataParallel and distributed training utilities for torch.rb. Split batches across multiple GPUs automatically.

Self-Organized Map implementation using torch-rb