image-match/python/py/Lib/site-packages/transformers/models/eurobert/configuration_eurobert.py

#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from src/transformers/models/eurobert/modular_eurobert.py.
#               Do NOT edit this file manually as any edits will be overwritten by the generation of
#             the file from the modular. If any change should be done, please apply the change to the
#                          modular_eurobert.py file directly. One of our CI enforces this.
#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# Copyright 2025 Nicolas Boizard, Duarte M. Alves, Hippolyte Gisserot-Boukhlef and the EuroBert 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.


from ...configuration_utils import strict
from ...modeling_rope_utils import RopeParameters
from ...utils import auto_docstring
from ..llama import LlamaConfig


@auto_docstring(checkpoint="EuroBERT/EuroBERT-210m")
@strict
class EuroBertConfig(LlamaConfig):
    r"""
    mask_token_id (`int`, *optional*, defaults to 128002):
        Mask token id.
    classifier_pooling (`str`, *optional*, defaults to `"late"`):
        The pooling strategy to use for the classifier. Can be one of ['bos', 'mean', 'late'].

    ```python
    >>> from transformers import EuroBertModel, EuroBertConfig

    >>> # Initializing a EuroBert eurobert-base style configuration
    >>> configuration = EuroBertConfig()

    >>> # Initializing a model from the eurobert-base style configuration
    >>> model = EuroBertModel(configuration)

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

    model_type = "eurobert"

    vocab_size: int = 128256
    hidden_size: int = 768
    intermediate_size: int = 3072
    num_hidden_layers: int = 12
    num_attention_heads: int = 12
    num_key_value_heads: int | None = None
    hidden_act: str = "silu"
    max_position_embeddings: int = 8192
    initializer_range: float = 0.02
    rms_norm_eps: float = 1e-05
    bos_token_id: int | None = 128000
    eos_token_id: int | list[int] | None = 128001
    pad_token_id: int | None = 128001
    mask_token_id: int = 128002
    pretraining_tp: int = 1
    tie_word_embeddings: bool = False
    rope_parameters: RopeParameters | dict | None = None
    attention_bias: bool = False
    attention_dropout: int | float = 0.0
    mlp_bias: bool = False
    head_dim: int | None = None
    classifier_pooling: str = "late"

    def __post_init__(self, **kwargs):
        if self.num_key_value_heads is None:
            self.num_key_value_heads = self.num_attention_heads
        super().__post_init__(**kwargs)


__all__ = ["EuroBertConfig"]