image-match/python/py/Lib/site-packages/transformers/models/yoso/configuration_yoso.py

# Copyright 2022 The HuggingFace Inc. team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""YOSO model configuration"""

from huggingface_hub.dataclasses import strict

from ...configuration_utils import PreTrainedConfig
from ...utils import auto_docstring


@auto_docstring(checkpoint="uw-madison/yoso-4096")
@strict
class YosoConfig(PreTrainedConfig):
    r"""
    use_expectation (`bool`, *optional*, defaults to `True`):
        Whether or not to use YOSO Expectation. Overrides any effect of num_hash.
    hash_code_len (`int`, *optional*, defaults to 9):
        The length of hashes generated by the hash functions.
    num_hash (`int`, *optional*, defaults to 64):
        Number of hash functions used in [`YosoSelfAttention`].
    conv_window (`int`, *optional*):
        Kernel size of depth-wise convolution.
    use_fast_hash (`bool`, *optional*, defaults to `False`):
        Whether or not to use custom cuda kernels which perform fast random projection via hadamard transform.
    lsh_backward (`bool`, *optional*, defaults to `True`):
        Whether or not to perform backpropagation using Locality Sensitive Hashing.

    Example:

    ```python
    >>> from transformers import YosoConfig, YosoModel

    >>> # Initializing a YOSO uw-madison/yoso-4096 style configuration
    >>> configuration = YosoConfig()

    >>> # Initializing a model (with random weights) from the uw-madison/yoso-4096 style configuration
    >>> model = YosoModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```"""

    model_type = "yoso"

    vocab_size: int = 50265
    hidden_size: int = 768
    num_hidden_layers: int = 12
    num_attention_heads: int = 12
    intermediate_size: int = 3072
    hidden_act: str = "gelu"
    hidden_dropout_prob: float | int = 0.1
    attention_probs_dropout_prob: float | int = 0.1
    max_position_embeddings: int = 4096
    type_vocab_size: int = 1
    initializer_range: float = 0.02
    layer_norm_eps: float = 1e-12
    use_expectation: bool = True
    hash_code_len: int = 9
    num_hash: int = 64
    conv_window: int | None = None
    use_fast_hash: bool = True
    lsh_backward: bool = True
    pad_token_id: int | None = 1
    bos_token_id: int | None = 0
    eos_token_id: int | list[int] | None = 2
    add_cross_attention: bool = False
    tie_word_embeddings: bool = True


__all__ = ["YosoConfig"]