GPTModel

java.lang.Object

io.github.kirstenali.deepj.models.gpt.GPTModel

All Implemented Interfaces:: Persistable, Trainable

public final class GPTModel extends Object implements Trainable, Persistable

Minimal GPT-style decoder-only transformer for educational/training use. CPU-only and dependency-free; intended for small models.

Constructor Summary

Constructors

Constructor

Description

GPTModel(GPTConfig cfg, long seed)
Method Summary

Modifier and Type

Method

Description

void

backward(Tensor dLogits)

Tensor

forward(int[] inputIds)

double

gradClipNorm()

List<Parameter>

parameters()

Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface io.github.kirstenali.deepj.persistence.Persistable
load, save

Methods inherited from interface io.github.kirstenali.deepj.training.Trainable
zeroGrad

Constructor Details
- GPTModel
  
  public GPTModel(GPTConfig cfg, long seed)
Method Details
- forward
  
  public Tensor forward(int[] inputIds)
- backward
  
  public void backward(Tensor dLogits)
- parameters
  
  public List<Parameter> parameters()
  
  Specified by:
  
  parameters in interface Persistable
  
  Specified by:
  
  parameters in interface Trainable
- gradClipNorm
  
  public double gradClipNorm()