Uses of Class
io.github.kirstenali.deepj.nn.transformer.DecoderOnlyModel

Packages that use DecoderOnlyModel

Package	Description
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.persistence

Uses of DecoderOnlyModel in io.github.kirstenali.deepj.nn.transformer

Methods in io.github.kirstenali.deepj.nn.transformer that return DecoderOnlyModel

Modifier and Type	Method	Description
static DecoderOnlyModel	ModelLoader.load(Path path)

Uses of DecoderOnlyModel in io.github.kirstenali.deepj.nn.transformer.loop

Subclasses of DecoderOnlyModel in io.github.kirstenali.deepj.nn.transformer.loop

Modifier and Type	Class	Description
final class	DeepJLoop	A looped causal decoder reusing grouped-query attention and SwiGLU blocks across passes.

Uses of DecoderOnlyModel in io.github.kirstenali.deepj.nn.transformer.nova

Subclasses of DecoderOnlyModel in io.github.kirstenali.deepj.nn.transformer.nova

Modifier and Type	Class	Description
final class	DeepJNova	A decoder with grouped-query attention, optional QK normalization, and tied embeddings.

Uses of DecoderOnlyModel in io.github.kirstenali.deepj.nn.transformer.orbit

Subclasses of DecoderOnlyModel in io.github.kirstenali.deepj.nn.transformer.orbit

Modifier and Type	Class	Description
final class	DeepJOrbit

Uses of DecoderOnlyModel in io.github.kirstenali.deepj.nn.transformer.origin

Subclasses of DecoderOnlyModel in io.github.kirstenali.deepj.nn.transformer.origin

Modifier and Type	Class	Description
final class	DeepJOrigin

Uses of DecoderOnlyModel in io.github.kirstenali.deepj.nn.transformer.prism

Subclasses of DecoderOnlyModel in io.github.kirstenali.deepj.nn.transformer.prism

Modifier and Type	Class	Description
final class	DeepJPrism

Uses of DecoderOnlyModel in io.github.kirstenali.deepj.persistence

Methods in io.github.kirstenali.deepj.persistence with parameters of type DecoderOnlyModel

Modifier and Type	Method	Description
static TrainingProgress	TrainingCheckpoint.load(DecoderOnlyModel model, AdamW optimizer, StatefulBatchSource dataset, CosineLearningRateSchedule schedule, Path path)
static void	TrainingCheckpoint.save(DecoderOnlyModel model, AdamW optimizer, StatefulBatchSource dataset, TrainingProgress progress, CosineLearningRateSchedule schedule, Path path)