DeepJ 0.13.0-alpha API

DeepJ is a Java neural network library for building, training, and running models. N-dimensional tensors, automatic differentiation, composable layers, and CPU/Metal backend operations form one shared foundation for feed-forward, convolutional, recurrent, autoencoder, and Transformer networks.

This reference documents DeepJ 0.13.0-alpha. Match your dependency version to the API reference.

Start with the documentation index for network, training, persistence, and backend guides. Decoder language-model APIs, tokenization, and chat tools are specialist parts of the library.

Packages

Package	Description
io.github.kirstenali.deepj.activations
io.github.kirstenali.deepj.autograd
io.github.kirstenali.deepj.chatui
io.github.kirstenali.deepj.cli
io.github.kirstenali.deepj.concurrent
io.github.kirstenali.deepj.data
io.github.kirstenali.deepj.examples
io.github.kirstenali.deepj.inference
io.github.kirstenali.deepj.layers
io.github.kirstenali.deepj.layers.transformer
io.github.kirstenali.deepj.layers.transformer.attention
io.github.kirstenali.deepj.layers.transformer.blocks
io.github.kirstenali.deepj.layers.transformer.norm
io.github.kirstenali.deepj.loss
io.github.kirstenali.deepj.nn	Neural networks composed from DeepJ tensors, layers, autograd and backend operations.
io.github.kirstenali.deepj.nn.transformer
io.github.kirstenali.deepj.nn.transformer.loop
io.github.kirstenali.deepj.nn.transformer.nova
io.github.kirstenali.deepj.nn.transformer.orbit
io.github.kirstenali.deepj.nn.transformer.origin
io.github.kirstenali.deepj.nn.transformer.prism
io.github.kirstenali.deepj.optimisers
io.github.kirstenali.deepj.persistence
io.github.kirstenali.deepj.publishing
io.github.kirstenali.deepj.tensor
io.github.kirstenali.deepj.tensor.cpu
io.github.kirstenali.deepj.tensor.metal
io.github.kirstenali.deepj.tokenizers
io.github.kirstenali.deepj.tokenizers.bpe
io.github.kirstenali.deepj.training
io.github.kirstenali.deepj.transformer
io.github.kirstenali.deepj.transformer.embeddings