# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨 # This file was automatically generated from src/transformers/models/got_ocr2/modular_got_ocr2.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_got_ocr2.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 GotOcr2VisionConfig(PretrainedConfig): r""" This is the configuration class to store the configuration of a [`GotOcr2VisionModel`]. It is used to instantiate a GOT_OCR2 vision encoder according to the specified arguments, defining the model architecture. Instantiating a configuration defaults will yield a similar configuration to that of the SAM ViT-h [facebook/sam-vit-huge](https://huggingface.co/facebook/sam-vit-huge) 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 768): Dimensionality of the encoder layers and the pooler layer. output_channels (`int`, *optional*, defaults to 256): Dimensionality of the output channels in the Patch 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 image. image_size (`int`, *optional*, defaults to 1024): Expected resolution. Target size of the resized input image. patch_size (`int`, *optional*, defaults to 16): Size of the patches to be extracted from the input image. hidden_act (`str`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) 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 query, key, value projections. use_abs_pos (`bool`, *optional*, defaults to `True`): Whether to use absolute position embedding. use_rel_pos (`bool`, *optional*, defaults to `True`): Whether to use relative position embedding. window_size (`int`, *optional*, defaults to 14): Window size for relative position. global_attn_indexes (`list[int]`, *optional*, defaults to `[2, 5, 8, 11]`): The indexes of the global attention layers. mlp_dim (`int`, *optional*, defaults to 3072): The dimensionality of the MLP layer in the Transformer encoder. """ base_config_key = "vision_config" def __init__( self, hidden_size=768, output_channels=256, num_hidden_layers=12, num_attention_heads=12, num_channels=3, image_size=1024, patch_size=16, hidden_act="gelu", layer_norm_eps=1e-06, attention_dropout=0.0, initializer_range=1e-10, qkv_bias=True, use_abs_pos=True, use_rel_pos=True, window_size=14, global_attn_indexes=[2, 5, 8, 11], mlp_dim=3072, **kwargs, ): super().__init__(**kwargs) self.hidden_size = hidden_size self.output_channels = output_channels self.num_hidden_layers = num_hidden_layers self.num_attention_heads = num_attention_heads self.num_channels = num_channels self.image_size = image_size self.patch_size = patch_size self.hidden_act = hidden_act self.layer_norm_eps = layer_norm_eps self.attention_dropout = attention_dropout self.initializer_range = initializer_range self.qkv_bias = qkv_bias self.use_abs_pos = use_abs_pos self.use_rel_pos = use_rel_pos self.window_size = window_size self.global_attn_indexes = global_attn_indexes self.mlp_dim = mlp_dim class GotOcr2Config(PretrainedConfig): r""" This is the configuration class to store the configuration of a [`GotOcr2ForConditionalGeneration`]. It is used to instantiate a GotOcr2 model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of GOT-OCR-2.0. e.g [stepfun-ai/GOT-OCR-2.0-hf](https://huggingface.co/stepfun-ai/GOT-OCR-2.0-hf) 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 151859): The image token index to encode the image prompt. image_seq_length (`int`, *optional*, defaults to 576): Sequence length of one image embedding. pad_token_id (`int`, *optional*, defaults to -1): Padding token id. ```python >>> from transformers import GotOcr2ForConditionalGeneration, GotOcr2Config >>> # Initializing a GotOcr2 style configuration >>> configuration = GotOcr2Config() >>> # Initializing a model from the Qwen2-VL-7B style configuration >>> model = GotOcr2ForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```""" model_type = "got_ocr2" attribute_map = { "image_token_id": "image_token_index", } sub_configs = {"text_config": AutoConfig, "vision_config": GotOcr2VisionConfig} def __init__( self, vision_config=None, text_config=None, image_token_index=151859, image_seq_length=576, pad_token_id=-1, **kwargs, ): self.image_token_index = image_token_index self.image_seq_length = image_seq_length self.pad_token_id = pad_token_id if vision_config is None: self.vision_config = GotOcr2VisionConfig() elif isinstance(vision_config, dict): self.vision_config = GotOcr2VisionConfig(**vision_config) elif isinstance(vision_config, GotOcr2VisionConfig): self.vision_config = vision_config if isinstance(text_config, dict): text_config["model_type"] = text_config.get("model_type", "qwen2") text_config = CONFIG_MAPPING[text_config["model_type"]](**text_config) elif text_config is None: text_config = CONFIG_MAPPING["qwen2"]( vocab_size=151860, hidden_size=1024, intermediate_size=2816, num_hidden_layers=24, num_attention_heads=16, num_key_value_heads=16, hidden_act="silu", max_position_embeddings=32768, initializer_range=0.02, rms_norm_eps=1e-6, use_cache=True, tie_word_embeddings=True, rope_theta=1000000.0, rope_scaling=None, use_sliding_window=False, sliding_window=4096, max_window_layers=21, attention_dropout=0.0, ) self.text_config = text_config super().__init__(**kwargs) __all__ = ["GotOcr2VisionConfig", "GotOcr2Config"]