configuration_aimv2.py

from typing import Any

from transformers.configuration_utils import PretrainedConfig

__all__ = ["AIMv2Config"]


class AIMv2Config(PretrainedConfig):
    """This is the configuration class to store the configuration of an [`AIMv2Model`].

    Instantiating a configuration with the defaults will yield a similar configuration
    to that of the [apple/aimv2-large-patch14-native](https://huggingface.co/apple/aimv2-large-patch14-native)

    Args:
        hidden_size: Dimension of the hidden representations.
        intermediate_size: Dimension of the SwiGLU representations.
        num_hidden_layers: Number of hidden layers in the Transformer.
        num_attention_heads: Number of attention heads for each attention layer
            in the Transformer.
        num_channels: Number of input channels.
        num_queries: Number of learnable queries in the head.
        patch_size: Patch size.
        rms_norm_eps: Epsilon value used for the RMS normalization layer.
        attention_dropout: Dropout ratio for attention probabilities.
        projection_dropout: Dropout ratio for the projection layer after the attention.
        qkv_bias: Whether to add a bias to the queries, keys and values.
        use_bias: Whether to add a bias in the feed-forward and projection layers.
        kwargs: Keyword arguments for the [`PretrainedConfig`].
    """

    model_type: str = "aimv2"

    def __init__(
        self,
        hidden_size: int = 1024,
        intermediate_size: int = 2816,
        num_hidden_layers: int = 24,
        num_attention_heads: int = 8,
        num_channels: int = 3,
        num_queries: int = 256,
        patch_size: int = 14,
        rms_norm_eps: float = 1e-5,
        attention_dropout: float = 0.0,
        projection_dropout: float = 0.0,
        qkv_bias: bool = False,
        use_bias: bool = False,
        **kwargs: Any,
    ):
        super().__init__(**kwargs)
        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.num_channels = num_channels
        self.num_queries = num_queries
        self.patch_size = patch_size
        self.attention_dropout = attention_dropout
        self.rms_norm_eps = rms_norm_eps

        self.projection_dropout = projection_dropout
        self.qkv_bias = qkv_bias
        self.use_bias = use_bias