Transformers

Module: generative_models.core.layers.transformers

Source: generative_models/core/layers/transformers.py

Overview

Transformer implementation with flexible positional encodings - FINAL CORRECTED VERSION.

This module provides transformer encoder and decoder implementations that support various types of positional encodings using the latest Flax NNX API.

Classes

FeedForwardNetwork

class FeedForwardNetwork

TransformerDecoder

class TransformerDecoder

TransformerDecoderBlock

class TransformerDecoderBlock

TransformerEncoder

class TransformerEncoder

TransformerEncoderBlock

class TransformerEncoderBlock

Functions

call

def __call__()

call

def __call__()

call

def __call__()

call

def __call__()

call

def __call__()

init

def __init__()

init

def __init__()

init

def __init__()

init

def __init__()

init

def __init__()

create_attention_mask

def create_attention_mask()

create_transformer

def create_transformer()

Module Statistics

• Classes: 5
• Functions: 12
• Imports: 6