configuration_modernbert.py

#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from src/transformers/models/modernbert/modular_modernbert.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_modernbert.py file directly. One of our CI enforces this.
#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# Copyright 2024 Answer.AI, LightOn, and contributors, and 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.

from typing import Literal

from transformers.configuration_utils import PretrainedConfig


class ModernBertConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`ModernBertModel`]. It is used to instantiate an ModernBert
    model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
    defaults will yield a similar configuration to that of the ModernBERT-base.
    e.g. [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base)

    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
    documentation from [`PretrainedConfig`] for more information.

    Args:
        vocab_size (`int`, *optional*, defaults to 50368):
            Vocabulary size of the ModernBert model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`ModernBertModel`]
        hidden_size (`int`, *optional*, defaults to 768):
            Dimension of the hidden representations.
        intermediate_size (`int`, *optional*, defaults to 1152):
            Dimension of the MLP representations.
        num_hidden_layers (`int`, *optional*, defaults to 22):
            Number of hidden layers in the Transformer decoder.
        num_attention_heads (`int`, *optional*, defaults to 12):
            Number of attention heads for each attention layer in the Transformer decoder.
        hidden_activation (`str` or `function`, *optional*, defaults to `"gelu"`):
            The non-linear activation function (function or string) in the decoder. Will default to `"gelu"`
            if not specified.
        max_position_embeddings (`int`, *optional*, defaults to 8192):
            The maximum sequence length that this model might ever be used with.
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        initializer_cutoff_factor (`float`, *optional*, defaults to 2.0):
            The cutoff factor for the truncated_normal_initializer for initializing all weight matrices.
        norm_eps (`float`, *optional*, defaults to 1e-05):
            The epsilon used by the rms normalization layers.
        norm_bias (`bool`, *optional*, defaults to `False`):
            Whether to use bias in the normalization layers.
        pad_token_id (`int`, *optional*, defaults to 50283):
            Padding token id.
        eos_token_id (`int`, *optional*, defaults to 50282):
            End of stream token id.
        bos_token_id (`int`, *optional*, defaults to 50281):
            Beginning of stream token id.
        cls_token_id (`int`, *optional*, defaults to 50281):
            Classification token id.
        sep_token_id (`int`, *optional*, defaults to 50282):
            Separation token id.
        global_rope_theta (`float`, *optional*, defaults to 160000.0):
            The base period of the global RoPE embeddings.
        attention_bias (`bool`, *optional*, defaults to `False`):
            Whether to use a bias in the query, key, value and output projection layers during self-attention.
        attention_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the attention probabilities.
        global_attn_every_n_layers (`int`, *optional*, defaults to 3):
            The number of layers between global attention layers.
        local_attention (`int`, *optional*, defaults to 128):
            The window size for local attention.
        local_rope_theta (`float`, *optional*, defaults to 10000.0):
            The base period of the local RoPE embeddings.
        embedding_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the embeddings.
        mlp_bias (`bool`, *optional*, defaults to `False`):
            Whether to use bias in the MLP layers.
        mlp_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the MLP layers.
        decoder_bias (`bool`, *optional*, defaults to `True`):
            Whether to use bias in the decoder layers.
        classifier_pooling (`str`, *optional*, defaults to `"cls"`):
            The pooling method for the classifier. Should be either `"cls"` or `"mean"`. In local attention layers, the
            CLS token doesn't attend to all tokens on long sequences.
        classifier_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the classifier.
        classifier_bias (`bool`, *optional*, defaults to `False`):
            Whether to use bias in the classifier.
        classifier_activation (`str`, *optional*, defaults to `"gelu"`):
            The activation function for the classifier.
        deterministic_flash_attn (`bool`, *optional*, defaults to `False`):
            Whether to use deterministic flash attention. If `False`, inference will be faster but not deterministic.
        sparse_prediction (`bool`, *optional*, defaults to `False`):
            Whether to use sparse prediction for the masked language model instead of returning the full dense logits.
        sparse_pred_ignore_index (`int`, *optional*, defaults to -100):
            The index to ignore for the sparse prediction.
        reference_compile (`bool`, *optional*):
            Whether to compile the layers of the model which were compiled during pretraining. If `None`, then parts of
            the model will be compiled if 1) `triton` is installed, 2) the model is not on MPS, 3) the model is not
            shared between devices, and 4) the model is not resized after initialization. If `True`, then the model may
            be faster in some scenarios.

    Examples:

    ```python
    >>> from transformers import ModernBertModel, ModernBertConfig

    >>> # Initializing a ModernBert style configuration
    >>> configuration = ModernBertConfig()

    >>> # Initializing a model from the modernbert-base style configuration
    >>> model = ModernBertModel(configuration)

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

    model_type = "modernbert"
    keys_to_ignore_at_inference = ["past_key_values"]

    def __init__(
        self,
        vocab_size=50368,
        hidden_size=768,
        intermediate_size=1152,
        num_hidden_layers=22,
        num_attention_heads=12,
        hidden_activation="gelu",
        max_position_embeddings=8192,
        initializer_range=0.02,
        initializer_cutoff_factor=2.0,
        norm_eps=1e-5,
        norm_bias=False,
        pad_token_id=50283,
        eos_token_id=50282,
        bos_token_id=50281,
        cls_token_id=50281,
        sep_token_id=50282,
        global_rope_theta=160000.0,
        attention_bias=False,
        attention_dropout=0.0,
        global_attn_every_n_layers=3,
        local_attention=128,
        local_rope_theta=10000.0,
        embedding_dropout=0.0,
        mlp_bias=False,
        mlp_dropout=0.0,
        decoder_bias=True,
        classifier_pooling: Literal["cls", "mean"] = "cls",
        classifier_dropout=0.0,
        classifier_bias=False,
        classifier_activation="gelu",
        deterministic_flash_attn=False,
        sparse_prediction=False,
        sparse_pred_ignore_index=-100,
        reference_compile=None,
        **kwargs,
    ):
        super().__init__(
            pad_token_id=pad_token_id,
            bos_token_id=bos_token_id,
            eos_token_id=eos_token_id,
            cls_token_id=cls_token_id,
            sep_token_id=sep_token_id,
            **kwargs,
        )
        self.vocab_size = vocab_size
        self.max_position_embeddings = max_position_embeddings
        self.hidden_size = hidden_size
        self.intermediate_size = intermediate_size
        self.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads
        self.initializer_range = initializer_range
        self.initializer_cutoff_factor = initializer_cutoff_factor
        self.norm_eps = norm_eps
        self.norm_bias = norm_bias
        self.global_rope_theta = global_rope_theta
        self.attention_bias = attention_bias
        self.attention_dropout = attention_dropout
        self.hidden_activation = hidden_activation
        self.global_attn_every_n_layers = global_attn_every_n_layers
        self.local_attention = local_attention
        self.local_rope_theta = local_rope_theta
        self.embedding_dropout = embedding_dropout
        self.mlp_bias = mlp_bias
        self.mlp_dropout = mlp_dropout
        self.decoder_bias = decoder_bias
        self.classifier_pooling = classifier_pooling
        self.classifier_dropout = classifier_dropout
        self.classifier_bias = classifier_bias
        self.classifier_activation = classifier_activation
        self.deterministic_flash_attn = deterministic_flash_attn
        self.sparse_prediction = sparse_prediction
        self.sparse_pred_ignore_index = sparse_pred_ignore_index
        self.reference_compile = reference_compile

        if self.classifier_pooling not in ["cls", "mean"]:
            raise ValueError(
                f'Invalid value for `classifier_pooling`, should be either "cls" or "mean", but is {self.classifier_pooling}.'
            )


__all__ = ["ModernBertConfig"]