| |
| |
| |
| |
| |
|
|
| import copy |
|
|
| from transformers import AutoConfig, LlamaConfig |
| from transformers.configuration_utils import PretrainedConfig |
| from transformers.utils import logging |
|
|
| from .configuration_intern_vit import InternVisionConfig |
| from .configuration_internlm2 import InternLM2Config |
|
|
| logger = logging.get_logger(__name__) |
|
|
|
|
| class PVCInternVLConfig(PretrainedConfig): |
| model_type = 'pvc_internvl' |
| is_composition = True |
|
|
| def __init__( |
| self, |
| vision_config=None, |
| llm_config=None, |
| use_backbone_lora=0, |
| use_llm_lora=0, |
| use_temporal=False, |
| pad2square=False, |
| select_layer=-1, |
| force_image_size=None, |
| downsample_ratio=0.5, |
| template=None, |
| dynamic_image_size=False, |
| use_thumbnail=False, |
| ps_version='v1', |
| min_dynamic_patch=1, |
| max_dynamic_patch=6, |
| image_repeat_time=1, |
| video_repeat_time=1, |
| tile_repeat_way=None, |
| mlp_add_ops=None, |
| **kwargs): |
| super().__init__(**kwargs) |
|
|
| if vision_config is None: |
| vision_config = {'architectures': ['InternVisionTemporalModel']} |
| logger.info('vision_config is None. Initializing the InternVisionConfig with default values.') |
|
|
| if llm_config is None: |
| llm_config = {'architectures': ['InternLM2ForCausalLM']} |
| logger.info('llm_config is None. Initializing the LlamaConfig config with default values (`LlamaConfig`).') |
|
|
| self.vision_config = InternVisionConfig(**vision_config) |
| if llm_config.get('architectures')[0] == 'LlamaForCausalLM': |
| self.llm_config = LlamaConfig(**llm_config) |
| elif llm_config.get('architectures')[0] == 'InternLM2ForCausalLM': |
| self.llm_config = InternLM2Config(**llm_config) |
| else: |
| raise ValueError('Unsupported architecture: {}'.format(llm_config.get('architectures')[0])) |
| self.use_backbone_lora = use_backbone_lora |
| self.use_llm_lora = use_llm_lora |
| self.use_temporal = use_temporal |
| self.pad2square = pad2square |
| self.select_layer = select_layer |
| self.force_image_size = force_image_size |
| self.downsample_ratio = downsample_ratio |
| self.template = template |
| self.dynamic_image_size = dynamic_image_size |
| self.use_thumbnail = use_thumbnail |
| self.ps_version = ps_version |
| self.min_dynamic_patch = min_dynamic_patch |
| self.max_dynamic_patch = max_dynamic_patch |
| self.image_repeat_time = image_repeat_time |
| self.video_repeat_time = video_repeat_time |
| self.tile_repeat_way = tile_repeat_way |
| self.mlp_add_ops = mlp_add_ops |
|
|
| logger.info(f'vision_select_layer: {self.select_layer}') |
| logger.info(f'mlp_add_ops: {self.mlp_add_ops}') |
| logger.info(f'ps_version: {self.ps_version}') |
| logger.info(f'min_dynamic_patch: {self.min_dynamic_patch}') |
| logger.info(f'max_dynamic_patch: {self.max_dynamic_patch}') |
| logger.info(f'image_repeat_time: {self.image_repeat_time}') |
| logger.info(f'video_repeat_time: {self.video_repeat_time}') |
| logger.info(f'tile_repeat_way: {self.tile_repeat_way}') |
| |
|
|
| 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['use_temporal'] = self.use_temporal |
| 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 |
| output['dynamic_image_size'] = self.dynamic_image_size |
| output['use_thumbnail'] = self.use_thumbnail |
| output['ps_version'] = self.ps_version |
| output['min_dynamic_patch'] = self.min_dynamic_patch |
| output['max_dynamic_patch'] = self.max_dynamic_patch |
| output['image_repeat_time'] = self.image_repeat_time |
| output['video_repeat_time'] = self.video_repeat_time |
| output['tile_repeat_way'] = self.tile_repeat_way |
| output['mlp_add_ops'] = self.mlp_add_ops |
|
|
| return output |
|
|
