AutoAndroidController/py/venv/Lib/site-packages/transformers/models/ijepa/configuration_ijepa.py

# coding=utf-8
# Copyright 2024 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.
"""I-JEPA model configuration"""

from ...configuration_utils import PretrainedConfig


class IJepaConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`IJepaModel`]. It is used to instantiate an IJEPA
    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 I-JEPA
    [facebook/ijepa_vith14_1k](https://huggingface.co/facebook/ijepa_vith14_1k) architecture.

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


    Args:
        hidden_size (`int`, *optional*, defaults to 768):
            Dimensionality of the encoder layers and the pooler layer.
        num_hidden_layers (`int`, *optional*, defaults to 12):
            Number of hidden layers in the Transformer encoder.
        num_attention_heads (`int`, *optional*, defaults to 12):
            Number of attention heads for each attention layer in the Transformer encoder.
        intermediate_size (`int`, *optional*, defaults to 3072):
            Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
        hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`):
            The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
            `"relu"`, `"selu"` and `"gelu_new"` are supported.
        hidden_dropout_prob (`float`, *optional*, defaults to 0.0):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the attention probabilities.
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        layer_norm_eps (`float`, *optional*, defaults to 1e-12):
            The epsilon used by the layer normalization layers.
        image_size (`int`, *optional*, defaults to 224):
            The size (resolution) of each image.
        patch_size (`int`, *optional*, defaults to 16):
            The size (resolution) of each patch.
        num_channels (`int`, *optional*, defaults to 3):
            The number of input channels.
        qkv_bias (`bool`, *optional*, defaults to `True`):
            Whether to add a bias to the queries, keys and values.
        pooler_output_size (`int`, *optional*):
           Dimensionality of the pooler layer. If None, defaults to `hidden_size`.
        pooler_act (`str`, *optional*, defaults to `"tanh"`):
           The activation function to be used by the pooler. Keys of ACT2FN are supported for Flax and
           Pytorch, and elements of https://www.tensorflow.org/api_docs/python/tf/keras/activations are
           supported for Tensorflow.

    Example:

    ```python
    >>> from transformers import IJepaConfig, IJepaModel

    >>> # Initializing a IJEPA ijepa-base-patch16-224 style configuration
    >>> configuration = IJepaConfig()

    >>> # Initializing a model (with random weights) from the ijepa-base-patch16-224 style configuration
    >>> model = IJepaModel(configuration)

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

    model_type = "ijepa"

    def __init__(
        self,
        hidden_size=768,
        num_hidden_layers=12,
        num_attention_heads=12,
        intermediate_size=3072,
        hidden_act="gelu",
        hidden_dropout_prob=0.0,
        attention_probs_dropout_prob=0.0,
        initializer_range=0.02,
        layer_norm_eps=1e-12,
        image_size=224,
        patch_size=16,
        num_channels=3,
        qkv_bias=True,
        pooler_output_size=None,
        pooler_act="tanh",
        **kwargs,
    ):
        super().__init__(**kwargs)

        self.hidden_size = hidden_size
        self.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads
        self.intermediate_size = intermediate_size
        self.hidden_act = hidden_act
        self.hidden_dropout_prob = hidden_dropout_prob
        self.attention_probs_dropout_prob = attention_probs_dropout_prob
        self.initializer_range = initializer_range
        self.layer_norm_eps = layer_norm_eps
        self.image_size = image_size
        self.patch_size = patch_size
        self.num_channels = num_channels
        self.qkv_bias = qkv_bias
        self.pooler_output_size = pooler_output_size if pooler_output_size else hidden_size
        self.pooler_act = pooler_act


__all__ = ["IJepaConfig"]