File size: 2,468 Bytes
d85e3a4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 | # copied from https://huggingface.co/apple/aimv2-huge-patch14-448
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-patch14-224](https://huggingface.co/apple/aimv2-large-patch14-224).
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.
image_size: Image size.
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,
image_size: int = 224,
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.patch_size = patch_size
self.image_size = image_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
|