credit.attend

Attributes

print_once

Classes

AttentionConfig
Attend	Base class for all neural network modules.

Functions

exists(val)
default(val, d)
once(fn)

Module Contents

class credit.attend.AttentionConfig

Bases: tuple

enable_flash

enable_math

enable_mem_efficient

credit.attend.exists(val)

credit.attend.default(val, d)

credit.attend.once(fn)

credit.attend.print_once

class credit.attend.Attend(dropout=0.0, flash=False, scale=None)

Bases: torch.nn.Module

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing them to be nested in a tree structure. You can assign the submodules as regular attributes:

import torch.nn as nn
import torch.nn.functional as F


class Model(nn.Module):
    def __init__(self) -> None:
        super().__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will also have their parameters converted when you call to(), etc.

Note

As per the example above, an __init__() call to the parent class must be made before assignment on the child.

Variables:

training (bool) – Boolean represents whether this module is in training or evaluation mode.

dropout = 0.0

scale = None

attn_dropout

flash = False

cpu_config

cuda_config = None

flash_attn(q, k, v)

forward(q, k, v)

einstein notation b - batch h - heads n, i, j - sequence length (base sequence length, source, target) d - feature dimension