# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨 # This file was automatically generated from src/transformers/models/video_llama_3/modular_video_llama_3.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_video_llama_3.py file directly. One of our CI enforces this. # 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨 # Copyright 2025 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 ...configuration_utils import PreTrainedConfig from ..auto import CONFIG_MAPPING, AutoConfig class VideoLlama3VisionConfig(PreTrainedConfig): """ This is the configuration class to store the configuration of a [`VideoLlama3VisionModel`]. It is used to instantiate a VideoLLaMA3 vision encoder model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of VideoLLaMA3-2B [lkhl/VideoLLaMA3-2B-Image-HF](https://huggingface.co/lkhl/VideoLLaMA3-2B-Image-HF). Args: hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. intermediate_size (`int`, *optional*, defaults to 3072): 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 12): 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. patch_size (`int`, *optional*, defaults to 16): The size (resolution) of each patch. hidden_act (`str` or `function`, *optional*, defaults to `"gelu_pytorch_tanh"`): 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. 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 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. """ model_type = "video_llama_3_vision" base_config_key = "vision_config" def __init__( self, hidden_size=768, intermediate_size=3072, num_hidden_layers=12, num_attention_heads=12, num_channels=3, patch_size=16, hidden_act="gelu_pytorch_tanh", layer_norm_eps=1e-6, attention_dropout=0.0, initializer_range=0.02, **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.attention_dropout = attention_dropout self.layer_norm_eps = layer_norm_eps self.hidden_act = hidden_act self.initializer_range = initializer_range class VideoLlama3Config(PreTrainedConfig): """ This is the configuration class to store the configuration of a [`VideoLlama3Model`]. It is used to instantiate a VideoLLaMA3 model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of VideoLLaMA3-2B [lkhl/VideoLLaMA3-2B-Image-HF](https://huggingface.co/lkhl/VideoLLaMA3-2B-Image-HF). Args: text_config (`Union[PreTrainedConfig, dict]`, *optional*, defaults to `Qwen2Config`): The config object or dictionary of the text backbone. vision_config (`Union[PreTrainedConfig, dict]`, *optional*, defaults to `VideoLlama3VisionConfig`): The config object or dictionary of the vision backbone. image_token_id (`int`, *optional*, defaults to 151655): The image token index to encode the image prompt. video_token_id (`int`, *optional*, defaults to 151656): The video token index to encode the image prompt. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether to tie weight embeddings """ model_type = "video_llama_3" sub_configs = {"vision_config": VideoLlama3VisionConfig, "text_config": AutoConfig} keys_to_ignore_at_inference = ["past_key_values"] def __init__( self, text_config=None, vision_config=None, image_token_id=151655, video_token_id=151656, tie_word_embeddings=False, **kwargs, ): if isinstance(vision_config, dict): self.vision_config = self.sub_configs["vision_config"](**vision_config) elif isinstance(vision_config, PreTrainedConfig): self.vision_config = vision_config elif vision_config is None: self.vision_config = self.sub_configs["vision_config"]() else: raise ValueError( f"vision_config must be of type `dict` or `PreTrainedConfig`, but got {type(vision_config)}." ) if isinstance(text_config, dict): self.text_config = CONFIG_MAPPING[text_config["model_type"]](**text_config) elif isinstance(text_config, PreTrainedConfig): self.text_config = text_config elif text_config is None: self.text_config = CONFIG_MAPPING["qwen2"]() else: raise ValueError(f"text_config must be of type `dict` or `PreTrainedConfig`, but got {type(text_config)}.") self.image_token_id = image_token_id self.video_token_id = video_token_id self.tie_word_embeddings = tie_word_embeddings super().__init__(**kwargs) __all__ = ["VideoLlama3VisionConfig", "VideoLlama3Config"]