Last commit not found
| # -------------------------------------------------------- | |
| # InternVL | |
| # Copyright (c) 2023 OpenGVLab | |
| # Licensed under The MIT License [see LICENSE for details] | |
| # -------------------------------------------------------- | |
| import copy | |
| from transformers import LlamaConfig | |
| from transformers.configuration_utils import PretrainedConfig | |
| from transformers.utils import logging | |
| from .configuration_intern_vit import InternVisionConfig | |
| logger = logging.get_logger(__name__) | |
| class InternVLChatConfig(PretrainedConfig): | |
| model_type = 'internvl_chat' | |
| is_composition = True | |
| def __init__( | |
| self, | |
| vision_config=None, | |
| llm_config=None, | |
| use_backbone_lora=0, | |
| use_llm_lora=0, | |
| pad2square=False, | |
| select_layer=-4, | |
| force_image_size=None, | |
| downsample_ratio=0.5, | |
| template=None, | |
| **kwargs): | |
| super().__init__(**kwargs) | |
| if vision_config is None: | |
| vision_config = {} | |
| logger.info('vision_config is None. Initializing the InternVisionConfig with default values.') | |
| if llm_config is None: | |
| llm_config = {} | |
| logger.info('llm_config is None. Initializing the LlamaConfig config with default values (`LlamaConfig`).') | |
| self.vision_config = InternVisionConfig(**vision_config) | |
| self.llm_config = LlamaConfig(**llm_config) | |
| self.use_backbone_lora = use_backbone_lora | |
| self.use_llm_lora = use_llm_lora | |
| self.pad2square = pad2square | |
| self.select_layer = select_layer | |
| self.force_image_size = force_image_size | |
| self.downsample_ratio = downsample_ratio | |
| self.template = template | |
| logger.info(f'vision_select_layer: {self.select_layer}') | |
| def to_dict(self): | |
| """ | |
| Serializes this instance to a Python dictionary. Override the default [`~PretrainedConfig.to_dict`]. | |
| Returns: | |
| `Dict[str, any]`: Dictionary of all the attributes that make up this configuration instance, | |
| """ | |
| output = copy.deepcopy(self.__dict__) | |
| output['vision_config'] = self.vision_config.to_dict() | |
| output['llm_config'] = self.llm_config.to_dict() | |
| output['model_type'] = self.__class__.model_type | |
| output['use_backbone_lora'] = self.use_backbone_lora | |
| output['use_llm_lora'] = self.use_llm_lora | |
| output['pad2square'] = self.pad2square | |
| output['select_layer'] = self.select_layer | |
| output['force_image_size'] = self.force_image_size | |
| output['downsample_ratio'] = self.downsample_ratio | |
| output['template'] = self.template | |
| return output | |