Module neuralops.tests.testing_utils

Classes

class DummyDistilBertAttention (dim=64)

Expand source code

class DummyDistilBertAttention(nn.Module):
    def __init__(self, dim=64):
        super().__init__()
        self.q_lin = nn.Linear(dim, dim)
        self.k_lin = nn.Linear(dim, dim)
        self.v_lin = nn.Linear(dim, dim)
        self.out_lin = nn.Linear(dim, dim)

    def forward(self, hidden_states, *args, **kwargs):
        return (hidden_states, None)

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 :meth:to, etc.

Note

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

:ivar training: Boolean represents whether this module is in training or evaluation mode. :vartype training: bool

Initialize internal Module state, shared by both nn.Module and ScriptModule.

Ancestors

• torch.nn.modules.module.Module

Methods

def forward(self, hidden_states, *args, **kwargs) ‑> Callable[..., typing.Any]

Expand source code

def forward(self, hidden_states, *args, **kwargs):
    return (hidden_states, None)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the :class:Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class MockConfig (**kwargs)

Expand source code

class MockConfig:
    def __init__(self, **kwargs):
        self.hidden_size = kwargs.get("hidden_size", kwargs.get("embed_dim", 64))
        self.embed_dim = self.hidden_size
        self.num_attention_heads = kwargs.get("num_attention_heads", kwargs.get("num_heads", 4))
        self.num_heads = self.num_attention_heads
        self.num_key_value_heads = kwargs.get("num_key_value_heads", 4)
        self.head_dim = kwargs.get("head_dim", 16)
        self.dropout = kwargs.get("dropout", kwargs.get("attention_dropout", 0.0))
        self.attention_dropout = self.dropout
        self.is_decoder = kwargs.get("is_decoder", False)
        self.model_type = kwargs.get("model_type", "bert")

        # Hyperparams
        self.rank = kwargs.get("rank", 16)
        self.lora_rank = kwargs.get("lora_rank", 16)
        self.lora_alpha = kwargs.get("lora_alpha", 32.0)
        self.page_size = kwargs.get("page_size", 4)
        self.k_experts = kwargs.get("k_experts", 2)
        self.svd_rank = kwargs.get("svd_rank", 4)
        self.alpha = kwargs.get("alpha", 1.5)

        self.max_position_embeddings = kwargs.get("max_seq_len", 128)
        self.max_seq_len = self.max_position_embeddings
        self.layer_norm_eps = kwargs.get("layer_norm_eps", 1e-12)
        self.window_size = kwargs.get("window_size", 4)
        self.block_size = kwargs.get("block_size", 4)
        self.top_k = kwargs.get("top_k", 2)

        for k, v in kwargs.items():
            setattr(self, k, v)