caio rtkclouds
rtkclouds
/ HexastoreAttention.py
Created
August 19, 2024 18:21
This code defines a custom attention mechanism and transformer layer based on the hexastore concept, which is typically used for efficiently querying triples in a knowledge graph (Subject, Predicate, Object).
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import torch | |
| import torch.nn as nn | |
| import torch.nn.functional as F | |
| class HexastoreAttention(nn.Module): | |
| def __init__(self, d_model, num_heads): | |
| super().__init__() | |
| self.d_model = d_model | |
| self.num_heads = num_heads | |
| self.head_dim = d_model // num_heads |
OlderNewer