# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨 # This file was automatically generated from src/transformers/models/llava_next_video/modular_llava_next_video.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_llava_next_video.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. from ...configuration_utils import PretrainedConfig from ..auto import CONFIG_MAPPING, AutoConfig class LlavaNextVideoConfig(PretrainedConfig): r""" This is the configuration class to store the configuration of a [`LlavaNextVideoForConditionalGeneration`]. It is used to instantiate an Llava-NeXT 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 [llava-hf/LLaVA-NeXT-Video-7B-hf](https://huggingface.co/llava-hf/LLaVA-NeXT-Video-7B-hf) model. 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 (`Union[AutoConfig, dict]`, *optional*, defaults to `CLIPVisionConfig`): The config object or dictionary of the vision backbone. text_config (`Union[AutoConfig, dict]`, *optional*, defaults to `LlamaConfig`): The config object or dictionary of the text backbone. image_token_index (`int`, *optional*, defaults to 32001): The image token index to encode the image prompt. projector_hidden_act (`str`, *optional*, defaults to `"gelu"`): The activation function used by the multimodal projector. multimodal_projector_bias (`bool`, *optional*, defaults to `True`): Whether to use bias in the multimodal projector. vision_feature_select_strategy (`str`, *optional*, defaults to `"default"`): The feature selection strategy used to select the vision feature from the vision backbone. Can be one of `"default"` or `"full"`. If `"default"`, the CLS token is removed from the vision features. If `"full"`, the full vision features are used. vision_feature_layer (`Union[int, List[int]]`, *optional*, defaults to -2): The index of the layer to select the vision feature. If multiple indices are provided, the vision feature of the corresponding indices will be concatenated to form the vision features. image_grid_pinpoints (`List`, *optional*, defaults to `[[336, 672], [672, 336], [672, 672], [1008, 336], [336, 1008]]`): A list of possible resolutions to use for processing high resolution images. Each item in the list should be a tuple or list of the form `(height, width)`. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether the model's input and output word embeddings should be tied. video_token_index (`int`, *optional*, defaults to 32000): The video token index to encode the image prompt. spatial_pool_mode (`str`, *optional*, defaults to `"average"`): Pooling mode to use for videos. Can be "average", "max" or "conv". spatial_pool_stride (`int`, *optional*, defaults to 2): Stride used in the pooling layer for videos. image_seq_length (`int`, *optional*, defaults to 576): Sequence length of one image embedding. video_seq_length (`int`, *optional*, defaults to 288): Sequence length of one video embedding. Example: ```python >>> from transformers import LlavaNextVideoForConditionalGeneration, LlavaNextVideoConfig, CLIPVisionConfig, LlamaConfig >>> # Initializing a CLIP-vision config >>> vision_config = CLIPVisionConfig() >>> # Initializing a Llama config >>> text_config = LlamaConfig() >>> configuration = LlavaNextVideoConfig(vision_config, text_config) >>> model = LlavaNextVideoForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```""" model_type = "llava_next_video" attribute_map = { "image_token_id": "image_token_index", "video_token_id": "video_token_index", } sub_configs = {"text_config": AutoConfig, "vision_config": AutoConfig} def __init__( self, vision_config=None, text_config=None, image_token_index=32001, projector_hidden_act="gelu", multimodal_projector_bias=True, vision_feature_select_strategy="default", vision_feature_layer=-2, image_grid_pinpoints=None, tie_word_embeddings=False, video_token_index=32000, spatial_pool_mode="average", spatial_pool_stride=2, image_seq_length=576, video_seq_length=288, **kwargs, ): self.video_token_index = video_token_index self.spatial_pool_mode = spatial_pool_mode self.spatial_pool_stride = spatial_pool_stride self.image_seq_length = image_seq_length self.video_seq_length = video_seq_length self.image_token_index = image_token_index self.projector_hidden_act = projector_hidden_act self.multimodal_projector_bias = multimodal_projector_bias if vision_feature_select_strategy not in ["default", "full"]: raise ValueError( "vision_feature_select_strategy should be one of 'default', 'full'." f"Got: {vision_feature_select_strategy}" ) self.vision_feature_select_strategy = vision_feature_select_strategy self.vision_feature_layer = vision_feature_layer image_grid_pinpoints = ( image_grid_pinpoints if image_grid_pinpoints is not None else [[336, 672], [672, 336], [672, 672], [1008, 336], [336, 1008]] ) self.image_grid_pinpoints = image_grid_pinpoints if isinstance(vision_config, dict): vision_config["model_type"] = ( vision_config["model_type"] if "model_type" in vision_config else "clip_vision_model" ) vision_config = CONFIG_MAPPING[vision_config["model_type"]](**vision_config) elif vision_config is None: vision_config = CONFIG_MAPPING["clip_vision_model"]( intermediate_size=4096, hidden_size=1024, patch_size=14, image_size=336, num_hidden_layers=24, num_attention_heads=16, vocab_size=32000, projection_dim=768, ) self.vision_config = vision_config if isinstance(text_config, dict): text_config["model_type"] = text_config["model_type"] if "model_type" in text_config else "llama" text_config = CONFIG_MAPPING[text_config["model_type"]](**text_config) elif text_config is None: text_config = CONFIG_MAPPING["llama"]() self.text_config = text_config super().__init__(tie_word_embeddings=tie_word_embeddings, **kwargs) __all__ = ["LlavaNextVideoConfig"]