File size: 4,401 Bytes
0e1e0cf | 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 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 | # --------------------------------------------------------
# InternVL
# Copyright (c) 2024 OpenGVLab
# Licensed under The MIT License [see LICENSE for details]
# --------------------------------------------------------
import os
from typing import Union
from transformers.configuration_utils import PretrainedConfig
from transformers.utils import logging
logger = logging.get_logger(__name__)
class InternVisionPatchConfig(PretrainedConfig):
r"""
This is the configuration class to store the configuration of a [`InternVisionModel`]. It is used to
instantiate a vision encoder according to the specified arguments, defining the model architecture.
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
documentation from [`PretrainedConfig`] for more information.
Args:
num_channels (`int`, *optional*, defaults to 3):
Number of color channels in the input images (e.g., 3 for RGB).
patch_size (`int`, *optional*, defaults to 14):
The size (resolution) of each patch.
image_size (`int`, *optional*, defaults to 224):
The size (resolution) of each image.
qkv_bias (`bool`, *optional*, defaults to `False`):
Whether to add a bias to the queries and values in the self-attention layers.
hidden_size (`int`, *optional*, defaults to 3200):
Dimensionality of the encoder layers and the pooler layer.
num_attention_heads (`int`, *optional*, defaults to 25):
Number of attention heads for each attention layer in the Transformer encoder.
intermediate_size (`int`, *optional*, defaults to 12800):
Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
qk_normalization (`bool`, *optional*, defaults to `True`):
Whether to normalize the queries and keys in the self-attention layers.
num_hidden_layers (`int`, *optional*, defaults to 48):
Number of hidden layers in the Transformer encoder.
use_flash_attn (`bool`, *optional*, defaults to `True`):
Whether to use flash attention mechanism.
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"` ``"gelu"` are supported.
layer_norm_eps (`float`, *optional*, defaults to 1e-6):
The epsilon used by the layer normalization layers.
dropout (`float`, *optional*, defaults to 0.0):
The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
drop_path_rate (`float`, *optional*, defaults to 0.0):
Dropout rate for stochastic depth.
attention_dropout (`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.
initializer_factor (`float`, *optional*, defaults to 0.1):
A factor for layer scale.
"""
model_type = 'intern_vit_patch'
def __init__(
self,
patch_size=14,
image_size=224,
hidden_size=3200,
**kwargs,
):
super().__init__(**kwargs)
self.hidden_size = hidden_size
self.patch_size = patch_size
self.image_size = image_size
@classmethod
def from_pretrained(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs) -> 'PretrainedConfig':
config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)
if 'vision_config' in config_dict:
config_dict = config_dict['vision_config']
if 'model_type' in config_dict and hasattr(cls, 'model_type') and config_dict['model_type'] != cls.model_type:
logger.warning(
f"You are using a model of type {config_dict['model_type']} to instantiate a model of type "
f'{cls.model_type}. This is not supported for all configurations of models and can yield errors.'
)
return cls.from_dict(config_dict, **kwargs)
|