|
import copy |
|
from transformers.configuration_utils import PretrainedConfig |
|
from transformers.utils import logging |
|
from transformers import AutoConfig |
|
from transformers.models.auto import CONFIG_MAPPING |
|
|
|
from .configuration_intern_vit import InternVisionConfig |
|
|
|
logger = logging.get_logger(__name__) |
|
|
|
class H2OVLChatConfig(PretrainedConfig): |
|
model_type = 'h2ovl_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, |
|
dynamic_image_size=False, |
|
use_thumbnail=False, |
|
ps_version='v1', |
|
min_dynamic_patch=1, |
|
max_dynamic_patch=6, |
|
use_msac=False, |
|
**kwargs): |
|
super().__init__(**kwargs) |
|
|
|
self.vision_config = InternVisionConfig(**vision_config) |
|
|
|
if llm_config["model_type"] in CONFIG_MAPPING: |
|
self.llm_config = CONFIG_MAPPING[llm_config["model_type"]](**llm_config) |
|
else: |
|
self.llm_config = AutoConfig.from_pretrained(llm_config["_name_or_path"], trust_remote_code=True) |
|
self.llm_config.update(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 |
|
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.use_msac = use_msac |
|
|
|
logger.info(f'vision_select_layer: {self.select_layer}') |
|
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}') |
|
|
|
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 |
|
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['use_msac'] = self.use_msac |
|
|
|
return output |
