Lightstar/venv/Lib/site-packages/transformers/models/instructblipvideo/configuration_instructblipvideo.py

#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from src/transformers/models/instructblipvideo/modular_instructblipvideo.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_instructblipvideo.py file directly. One of our CI enforces this.
#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# coding=utf-8
# Copyright 2024 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.

import os
from typing import Union

from ...configuration_utils import PretrainedConfig
from ...models.auto.modeling_auto import MODEL_FOR_CAUSAL_LM_MAPPING_NAMES
from ...utils import logging
from ..auto import CONFIG_MAPPING


logger = logging.get_logger(__name__)


class InstructBlipVideoVisionConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`InstructBlipVideoVisionModel`]. It is used to
    instantiate a InstructBlipVideo vision encoder according to the specified arguments, defining the model architecture.
    Instantiating a configuration defaults will yield a similar configuration to that of the InstructBlipVideo
    [Salesforce/instruct-blip-flan-t5](https://huggingface.co/Salesforce/instruct-blip-flan-t5) 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 1408):
            Dimensionality of the encoder layers and the pooler layer.
        intermediate_size (`int`, *optional*, defaults to 6144):
            Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
        num_hidden_layers (`int`, *optional*, defaults to 39):
            Number of hidden layers in the Transformer encoder.
        num_attention_heads (`int`, *optional*, defaults to 16):
            Number of attention heads for each attention layer in the Transformer encoder.
        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.
        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. to 1e-5): The epsilon used by the layer
            normalization layers.
        layer_norm_eps (`float`, *optional*, defaults to 1e-06):
            The epsilon used by the layer normalization layers.
        attention_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the attention probabilities.
        initializer_range (`float`, *optional*, defaults to 1e-10):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        qkv_bias (`bool`, *optional*, defaults to `True`):
            Whether to add a bias to the queries and values in the self-attention layers.

    Example:

    ```python
    >>> from transformers import InstructBlipVideoVisionConfig, InstructBlipVideoVisionModel

    >>> # Initializing a InstructBlipVideoVisionConfig with Salesforce/instruct-blip-flan-t5 style configuration
    >>> configuration = InstructBlipVideoVisionConfig()

    >>> # Initializing a InstructBlipVideoVisionModel (with random weights) from the Salesforce/instruct-blip-flan-t5 style configuration
    >>> model = InstructBlipVideoVisionModel(configuration)

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

    model_type = "instructblipvideo_vision_model"

    def __init__(
        self,
        hidden_size=1408,
        intermediate_size=6144,
        num_hidden_layers=39,
        num_attention_heads=16,
        image_size=224,
        patch_size=14,
        hidden_act="gelu",
        layer_norm_eps=1e-6,
        attention_dropout=0.0,
        initializer_range=1e-10,
        qkv_bias=True,
        **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.patch_size = patch_size
        self.image_size = image_size
        self.initializer_range = initializer_range
        self.attention_dropout = attention_dropout
        self.layer_norm_eps = layer_norm_eps
        self.hidden_act = hidden_act
        self.qkv_bias = qkv_bias

    @classmethod
    def from_pretrained(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs) -> "PretrainedConfig":
        cls._set_token_in_kwargs(kwargs)

        config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)

        # get the vision config dict if we are loading from InstructBlipVideoConfig
        if config_dict.get("model_type") == "instructblipvideo":
            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)


class InstructBlipVideoQFormerConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`InstructBlipVideoQFormerModel`]. It is used to
    instantiate a InstructBlipVideo Querying Transformer (Q-Former) 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 InstructBlipVideo [Salesforce/instruct-blip-flan-t5](https://huggingface.co/Salesforce/instruct-blip-flan-t5)
    architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs.
    Read the documentation from [`PretrainedConfig`] for more information.

    Note that [`InstructBlipVideoQFormerModel`] is very similar to [`BertLMHeadModel`] with interleaved cross-attention.

    Args:
        vocab_size (`int`, *optional*, defaults to 30522):
            Vocabulary size of the Q-Former model. Defines the number of different tokens that can be represented by
            the `inputs_ids` passed when calling the model.
        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" (often named feed-forward) layer in the Transformer encoder.
        hidden_act (`str` or `Callable`, *optional*, defaults to `"gelu"`):
            The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
            `"relu"`, `"silu"` and `"gelu_new"` are supported.
        hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
            The dropout ratio for the attention probabilities.
        max_position_embeddings (`int`, *optional*, defaults to 512):
            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 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.
        pad_token_id (`int`, *optional*, defaults to 0):
            Token id used for padding sequences.
        position_embedding_type (`str`, *optional*, defaults to `"absolute"`):
            Type of position embedding. Choose one of `"absolute"`, `"relative_key"`, `"relative_key_query"`. For
            positional embeddings use `"absolute"`. For more information on `"relative_key"`, please refer to
            [Self-Attention with Relative Position Representations (Shaw et al.)](https://arxiv.org/abs/1803.02155).
            For more information on `"relative_key_query"`, please refer to *Method 4* in [Improve Transformer Models
            with Better Relative Position Embeddings (Huang et al.)](https://arxiv.org/abs/2009.13658).
        cross_attention_frequency (`int`, *optional*, defaults to 2):
            The frequency of adding cross-attention to the Transformer layers.
        encoder_hidden_size (`int`, *optional*, defaults to 1408):
            The hidden size of the hidden states for cross-attention.

    Examples:

    ```python
    >>> from transformers import InstructBlipVideoQFormerConfig, InstructBlipVideoQFormerModel

    >>> # Initializing a InstructBlipVideo Salesforce/instruct-blip-flan-t5 style configuration
    >>> configuration = InstructBlipVideoQFormerConfig()

    >>> # Initializing a model (with random weights) from the Salesforce/instruct-blip-flan-t5 style configuration
    >>> model = InstructBlipVideoQFormerModel(configuration)
    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```"""

    model_type = "instructblipvideo_qformer"

    def __init__(
        self,
        vocab_size=30522,
        hidden_size=768,
        num_hidden_layers=12,
        num_attention_heads=12,
        intermediate_size=3072,
        hidden_act="gelu",
        hidden_dropout_prob=0.1,
        attention_probs_dropout_prob=0.1,
        max_position_embeddings=512,
        initializer_range=0.02,
        layer_norm_eps=1e-12,
        pad_token_id=0,
        position_embedding_type="absolute",
        cross_attention_frequency=2,
        encoder_hidden_size=1408,
        **kwargs,
    ):
        super().__init__(pad_token_id=pad_token_id, **kwargs)

        self.vocab_size = vocab_size
        self.hidden_size = hidden_size
        self.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads
        self.hidden_act = hidden_act
        self.intermediate_size = intermediate_size
        self.hidden_dropout_prob = hidden_dropout_prob
        self.attention_probs_dropout_prob = attention_probs_dropout_prob
        self.max_position_embeddings = max_position_embeddings
        self.initializer_range = initializer_range
        self.layer_norm_eps = layer_norm_eps
        self.position_embedding_type = position_embedding_type
        self.cross_attention_frequency = cross_attention_frequency
        self.encoder_hidden_size = encoder_hidden_size

    @classmethod
    def from_pretrained(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs) -> "PretrainedConfig":
        cls._set_token_in_kwargs(kwargs)

        config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)

        # get the qformer config dict if we are loading from InstructBlipVideoConfig
        if config_dict.get("model_type") == "instructblipvideo":
            config_dict = config_dict["qformer_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)


class InstructBlipVideoConfig(PretrainedConfig):
    r"""
    [`InstructBlipVideoConfig`] is the configuration class to store the configuration of a
    [`InstructBlipVideoForConditionalGeneration`]. It is used to instantiate a Instructblipvideo model according to the specified
    arguments, defining the vision model, Q-Former model and language model configs. Instantiating a configuration with
    the defaults will yield a similar configuration to that of the Instructblipvideo
    [Salesforce/instruct-blip-flan-t5](https://huggingface.co/Salesforce/instruct-blip-flan-t5) architecture.

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

    Args:
        vision_config (`dict`, *optional*):
            Dictionary of configuration options used to initialize [`InstructBlipVideoVisionConfig`].
        qformer_config (`dict`, *optional*):
            Dictionary of configuration options used to initialize [`InstructBlipVideoQFormerConfig`].
        text_config (`dict`, *optional*):
            Dictionary of configuration options used to initialize any [`PretrainedConfig`].
        num_query_tokens (`int`, *optional*, defaults to 32):
            The number of query tokens passed through the Transformer.

        video_token_index (`int`, *optional*):
            Token index of special video token.
        kwargs (*optional*):
            Dictionary of keyword arguments.

    Example:

    ```python
    >>> from transformers import (
    ...     InstructBlipVideoVisionConfig,
    ...     InstructBlipVideoQFormerConfig,
    ...     OPTConfig,
    ...     InstructBlipVideoConfig,
    ...     InstructBlipVideoForConditionalGeneration,
    ... )

    >>> # Initializing a InstructBlipVideoConfig with Salesforce/instruct-blip-flan-t5 style configuration
    >>> configuration = InstructBlipVideoConfig()

    >>> # Initializing a InstructBlipVideoForConditionalGeneration (with random weights) from the Salesforce/instruct-blip-flan-t5 style configuration
    >>> model = InstructBlipVideoForConditionalGeneration(configuration)

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

    >>> # We can also initialize a InstructBlipVideoConfig from a InstructBlipVideoVisionConfig, InstructBlipVideoQFormerConfig and any PretrainedConfig

    >>> # Initializing Instructblipvideo vision, Instructblipvideo Q-Former and language model configurations
    >>> vision_config = InstructBlipVideoVisionConfig()
    >>> qformer_config = InstructBlipVideoQFormerConfig()
    >>> text_config = OPTConfig()

    >>> config = InstructBlipVideoConfig.from_text_vision_configs(vision_config, qformer_config, text_config)
    ```"""

    model_type = "instructblipvideo"

    def __init__(
        self,
        vision_config=None,
        qformer_config=None,
        text_config=None,
        num_query_tokens=32,
        video_token_index=None,
        **kwargs,
    ):
        super().__init__(**kwargs)

        if vision_config is None:
            vision_config = {}
            logger.info("vision_config is None. initializing the InstructBlipVideoVisionConfig with default values.")

        if qformer_config is None:
            qformer_config = {}
            logger.info("qformer_config is None. Initializing the InstructBlipVideoQFormerConfig with default values.")

        if text_config is None:
            text_config = {}
            logger.info("text_config is None. Initializing the text config with default values (`OPTConfig`).")

        self.vision_config = InstructBlipVideoVisionConfig(**vision_config)
        self.qformer_config = InstructBlipVideoQFormerConfig(**qformer_config)
        text_model_type = text_config["model_type"] if "model_type" in text_config else "opt"
        self.text_config = CONFIG_MAPPING[text_model_type](**text_config)

        self.tie_word_embeddings = self.text_config.tie_word_embeddings
        self.is_encoder_decoder = self.text_config.is_encoder_decoder

        self.num_query_tokens = num_query_tokens
        self.video_token_index = video_token_index
        self.qformer_config.encoder_hidden_size = self.vision_config.hidden_size
        self.use_decoder_only_language_model = self.text_config.model_type in MODEL_FOR_CAUSAL_LM_MAPPING_NAMES
        self.initializer_factor = 1.0
        self.initializer_range = 0.02

    @classmethod
    def from_vision_qformer_text_configs(
        cls,
        vision_config: InstructBlipVideoVisionConfig,
        qformer_config: InstructBlipVideoQFormerConfig,
        text_config: PretrainedConfig,
        **kwargs,
    ):
        r"""
        Instantiate a [`InstructBlipVideoConfig`] (or a derived class) from a InstructBlipVideo vision model, Q-Former and
        language model configurations.

        Returns:
            [`InstructBlipVideoConfig`]: An instance of a configuration object
        """

        return cls(
            vision_config=vision_config.to_dict(),
            qformer_config=qformer_config.to_dict(),
            text_config=text_config.to_dict(),
            **kwargs,
        )