297 lines
14 KiB
Python
297 lines
14 KiB
Python
|
# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
|
||
|
|
# This file was automatically generated from src/transformers/models/aimv2/modular_aimv2.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_aimv2.py file directly. One of our CI enforces this.
|
||
|
|
# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
|
||
|
|
# coding=utf-8
|
||
|
|
# Copyright 2025 Apple Inc. and The HuggingFace 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 Optional
|
||
|
|
|
||
|
|
from ...configuration_utils import PretrainedConfig
|
||
|
|
from ...utils import logging
|
||
|
|
|
||
|
|
|
||
|
|
logger = logging.get_logger(__name__)
|
||
|
|
|
||
|
|
|
||
|
|
class Aimv2VisionConfig(PretrainedConfig):
|
||
|
|
r"""
|
||
|
|
This is the configuration class to store the configuration of a [`Aimv2VisionModel`]. It is used to instantiate a
|
||
|
|
AIMv2 vision encoder according to the specified arguments, defining the model architecture. Instantiating a
|
||
|
|
configuration with the defaults will yield a similar configuration to that of the vision encoder of the AIMv2
|
||
|
|
[apple/aimv2-large-patch14-224](https://huggingface.co/apple/aimv2-large-patch14-224) 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 1024):
|
||
|
|
Dimensionality of the encoder layers and the pooler layer.
|
||
|
|
intermediate_size (`int`, *optional*, defaults to 2816):
|
||
|
|
Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
|
||
|
|
num_hidden_layers (`int`, *optional*, defaults to 24):
|
||
|
|
Number of hidden layers in the Transformer encoder.
|
||
|
|
num_attention_heads (`int`, *optional*, defaults to 8):
|
||
|
|
Number of attention heads for each attention layer in the Transformer encoder.
|
||
|
|
num_channels (`int`, *optional*, defaults to 3):
|
||
|
|
Number of channels in the input images.
|
||
|
|
image_size (`int`, *optional*, defaults to 224):
|
||
|
|
The size (resolution) of each image.
|
||
|
|
patch_size (`int`, *optional*, defaults to 14):
|
||
|
|
The size (resolution) of each patch.
|
||
|
|
rms_norm_eps (`float`, *optional*, defaults to 1e-05):
|
||
|
|
The epsilon used by the rms normalization layers.
|
||
|
|
attention_dropout (`float`, *optional*, defaults to 0.0):
|
||
|
|
The dropout ratio for the attention probabilities.
|
||
|
|
qkv_bias (`bool`, *optional*, defaults to `False`):
|
||
|
|
Whether to add a bias to the queries, keys and values.
|
||
|
|
mlp_bias (`bool`, *optional*, defaults to `False`):
|
||
|
|
Whether to add a bias to the Linear layers or Not.
|
||
|
|
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
|
||
|
|
The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
|
||
|
|
`"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported.
|
||
|
|
initializer_range (`float`, *optional*, defaults to 0.02):
|
||
|
|
The standard deviation of the for initializing all weight matrices.
|
||
|
|
use_head (`str`, *optional*, defaults to `True`):
|
||
|
|
Whether to use Attention Pooling Head or Not.
|
||
|
|
is_native (`str`, *optional*, defaults to `False`):
|
||
|
|
Whether to use ckpt trained for image native resolution or not.
|
||
|
|
Example:
|
||
|
|
|
||
|
|
```python
|
||
|
|
>>> from transformers import SiglipVisionConfig, SiglipVisionModel
|
||
|
|
|
||
|
|
>>> # Initializing a Aimv2VisionConfig with apple/aimv2-large-patch14-224 style configuration
|
||
|
|
>>> configuration = Aimv2VisionConfig()
|
||
|
|
|
||
|
|
>>> # Initializing a Aimv2VisionModel (with random weights) from the apple/aimv2-large-patch14-224 style configuration
|
||
|
|
>>> model = Aimv2VisionModel(configuration)
|
||
|
|
|
||
|
|
>>> # Accessing the model configuration
|
||
|
|
>>> configuration = model.config
|
||
|
|
```"""
|
||
|
|
|
||
|
|
model_type = "aimv2_vision_model"
|
||
|
|
base_config_key = "vision_config"
|
||
|
|
|
||
|
|
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,
|
||
|
|
qkv_bias: bool = False,
|
||
|
|
mlp_bias: bool = False,
|
||
|
|
hidden_act: str = "silu",
|
||
|
|
initializer_range: float = 0.02,
|
||
|
|
use_head: bool = True,
|
||
|
|
is_native: bool = False,
|
||
|
|
**kwargs,
|
||
|
|
):
|
||
|
|
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.hidden_act = hidden_act
|
||
|
|
|
||
|
|
self.use_head = use_head
|
||
|
|
self.initializer_range = initializer_range
|
||
|
|
self.mlp_bias = mlp_bias
|
||
|
|
self.qkv_bias = qkv_bias
|
||
|
|
self.rms_norm_eps = rms_norm_eps
|
||
|
|
self.is_native = is_native
|
||
|
|
|
||
|
|
|
||
|
|
class Aimv2TextConfig(PretrainedConfig):
|
||
|
|
r"""
|
||
|
|
This is the configuration class to store the configuration of a [`Aimv2TextModel`]. It is used to instantiate a
|
||
|
|
AIMv2 text encoder according to the specified arguments, defining the model architecture. Instantiating a
|
||
|
|
configuration with the defaults will yield a similar configuration to that of the text encoder of the AIMv2
|
||
|
|
[apple/aimv2-large-patch14-224-lit](https://huggingface.co/apple/aimv2-large-patch14-224-lit) architecture.
|
||
|
|
|
||
|
|
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 49408):
|
||
|
|
Vocabulary size of the AIMv2 text model. Defines the number of different tokens that can be represented by
|
||
|
|
the `inputs_ids` passed when calling [`Aimv2Model`].
|
||
|
|
hidden_size (`int`, *optional*, defaults to 768):
|
||
|
|
Dimensionality of the encoder layers and the pooler layer.
|
||
|
|
intermediate_size (`int`, *optional*, defaults to 2048):
|
||
|
|
Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
|
||
|
|
num_hidden_layers (`int`, *optional*, defaults to 12):
|
||
|
|
Number of hidden layers in the Transformer encoder.
|
||
|
|
num_attention_heads (`int`, *optional*, defaults to 6):
|
||
|
|
Number of attention heads for each attention layer in the Transformer encoder.
|
||
|
|
rms_norm_eps (`float`, *optional*, defaults to 1e-05):
|
||
|
|
The epsilon used by the rms normalization layers.
|
||
|
|
attention_dropout (`float`, *optional*, defaults to 0.0):
|
||
|
|
The dropout ratio for the attention probabilities.
|
||
|
|
qkv_bias (`bool`, *optional*, defaults to `False`):
|
||
|
|
Whether to add a bias to the queries, keys and values.
|
||
|
|
mlp_bias (`bool`, *optional*, defaults to `False`):
|
||
|
|
Whether to add a bias to the Linear layers or Not.
|
||
|
|
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
|
||
|
|
The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
|
||
|
|
`"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported.
|
||
|
|
pad_token_id (`int`, *optional*, defaults to 1):
|
||
|
|
The id of the padding token in the vocabulary.
|
||
|
|
bos_token_id (`int`, *optional*, defaults to 49406):
|
||
|
|
The id of the beginning-of-sequence token in the vocabulary.
|
||
|
|
eos_token_id (`int`, *optional*, defaults to 49407):
|
||
|
|
The id of the end-of-sequence token in the vocabulary.
|
||
|
|
max_position_embeddings (`int`, *optional*, defaults to 77):
|
||
|
|
The maximum sequence length that this model might ever be used with. Typically set this to something large
|
||
|
|
just in case (e.g., 512 or 1024 or 2048).
|
||
|
|
initializer_range (`float`, *optional*, defaults to 0.02):
|
||
|
|
The standard deviation of the for initializing all weight matrices.
|
||
|
|
"""
|
||
|
|
|
||
|
|
model_type = "aimv2_text_model"
|
||
|
|
base_config_key = "text_config"
|
||
|
|
|
||
|
|
def __init__(
|
||
|
|
self,
|
||
|
|
vocab_size: int = 49408,
|
||
|
|
hidden_size: int = 768,
|
||
|
|
intermediate_size: int = 2048,
|
||
|
|
num_hidden_layers: int = 12,
|
||
|
|
num_attention_heads: int = 6,
|
||
|
|
rms_norm_eps: float = 1e-5,
|
||
|
|
attention_dropout: float = 0.0,
|
||
|
|
qkv_bias: bool = False,
|
||
|
|
mlp_bias: bool = False,
|
||
|
|
hidden_act: str = "silu",
|
||
|
|
pad_token_id: Optional[int] = None,
|
||
|
|
bos_token_id: Optional[int] = None,
|
||
|
|
eos_token_id: int = 49407,
|
||
|
|
max_position_embeddings: int = 77,
|
||
|
|
initializer_range: bool = 0.02,
|
||
|
|
**kwargs,
|
||
|
|
):
|
||
|
|
super().__init__(pad_token_id=pad_token_id, bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)
|
||
|
|
|
||
|
|
self.vocab_size = vocab_size
|
||
|
|
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.max_position_embeddings = max_position_embeddings
|
||
|
|
self.hidden_act = hidden_act
|
||
|
|
self.attention_dropout = attention_dropout
|
||
|
|
|
||
|
|
self.initializer_range = initializer_range
|
||
|
|
self.mlp_bias = mlp_bias
|
||
|
|
self.qkv_bias = qkv_bias
|
||
|
|
self.rms_norm_eps = rms_norm_eps
|
||
|
|
|
||
|
|
|
||
|
|
class Aimv2Config(PretrainedConfig):
|
||
|
|
r"""
|
||
|
|
[`Aimv2Config`] is the configuration class to store the configuration of a [`Aimv2Model`]. It is used to
|
||
|
|
instantiate a AIMv2 model according to the specified arguments, defining the text model and vision model configs.
|
||
|
|
Instantiating a configuration with the defaults will yield a similar configuration to that of the AIMv2
|
||
|
|
[apple/aimv2-large-patch14-224-lit](https://huggingface.co/apple/aimv2-large-patch14-224-lit) architecture.
|
||
|
|
|
||
|
|
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
||
|
|
documentation from [`PretrainedConfig`] for more information.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
text_config (`dict`, *optional*):
|
||
|
|
Dictionary of configuration options used to initialize [`Aimv2TextConfig`].
|
||
|
|
vision_config (`dict`, *optional*):
|
||
|
|
Dictionary of configuration options used to initialize [`Aimv2VisionConfig`].
|
||
|
|
projection_dim (`int`, *optional*, defaults to 512):
|
||
|
|
Dimensionality of text and vision projection layers.
|
||
|
|
logit_scale_init_value (`float`, *optional*, defaults to 2.6592):
|
||
|
|
The initial value of the *logit_scale* parameter.
|
||
|
|
kwargs (*optional*):
|
||
|
|
Dictionary of keyword arguments.
|
||
|
|
|
||
|
|
Example:
|
||
|
|
|
||
|
|
```python
|
||
|
|
>>> from transformers import Aimv2Config, Aimv2Model
|
||
|
|
|
||
|
|
>>> # Initializing a Aimv2Config with apple/aimv2-large-patch14-224-lit style configuration
|
||
|
|
>>> configuration = Aimv2Config()
|
||
|
|
|
||
|
|
>>> # Initializing a Aimv2Model (with random weights) from the apple/aimv2-large-patch14-224-lit style configuration
|
||
|
|
>>> model = Aimv2Model(configuration)
|
||
|
|
|
||
|
|
>>> # Accessing the model configuration
|
||
|
|
>>> configuration = model.config
|
||
|
|
|
||
|
|
>>> # We can also initialize a Aimv2Config from a Aimv2TextConfig and a Aimv2VisionConfig
|
||
|
|
>>> from transformers import Aimv2TextConfig, Aimv2VisionConfig
|
||
|
|
|
||
|
|
>>> # Initializing a AIMv2Text and AIMv2Vision configuration
|
||
|
|
>>> config_text = Aimv2TextConfig()
|
||
|
|
>>> config_vision = Aimv2VisionConfig()
|
||
|
|
|
||
|
|
>>> config = Aimv2Config(text_config=config_text, vision_config=config_vision)
|
||
|
|
```"""
|
||
|
|
|
||
|
|
model_type = "aimv2"
|
||
|
|
sub_configs = {"text_config": Aimv2TextConfig, "vision_config": Aimv2VisionConfig}
|
||
|
|
|
||
|
|
def __init__(
|
||
|
|
self, text_config=None, vision_config=None, projection_dim=512, logit_scale_init_value=2.6592, **kwargs
|
||
|
|
):
|
||
|
|
super().__init__(**kwargs)
|
||
|
|
|
||
|
|
if text_config is None:
|
||
|
|
text_config = {}
|
||
|
|
logger.info("`text_config` is `None`. Initializing the `Aimv2TextConfig` with default values.")
|
||
|
|
|
||
|
|
if vision_config is None:
|
||
|
|
vision_config = {}
|
||
|
|
logger.info("`vision_config` is `None`. initializing the `Aimv2VisionConfig` with default values.")
|
||
|
|
|
||
|
|
self.text_config = Aimv2TextConfig(**text_config)
|
||
|
|
self.vision_config = Aimv2VisionConfig(**vision_config)
|
||
|
|
self.projection_dim = projection_dim
|
||
|
|
self.logit_scale_init_value = logit_scale_init_value
|
||
|
|
self.max_logit_scale = 100.0
|
||
|
|
|
||
|
|
@classmethod
|
||
|
|
def from_text_vision_configs(cls, text_config: Aimv2TextConfig, vision_config: Aimv2VisionConfig, **kwargs):
|
||
|
|
r"""
|
||
|
|
Instantiate a [`Aimv2Config`] (or a derived class) from aimv2 text model configuration and aimv2 vision
|
||
|
|
model configuration.
|
||
|
|
|
||
|
|
Returns:
|
||
|
|
[`Aimv2Config`]: An instance of a configuration object
|
||
|
|
"""
|
||
|
|
|
||
|
|
return cls(text_config=text_config.to_dict(), vision_config=vision_config.to_dict(), **kwargs)
|
||
|
|
|
||
|
|
|
||
|
|
__all__ = ["Aimv2Config", "Aimv2VisionConfig", "Aimv2TextConfig"]
|