File size: 3,992 Bytes
20f5bc9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 |
# --------------------------------------------------------
# NaViL
# Copyright (c) 2025 OpenGVLab
# Licensed under The MIT License [see LICENSE for details]
# --------------------------------------------------------
import copy
from transformers import AutoConfig, LlamaConfig
from transformers.configuration_utils import PretrainedConfig
from transformers.utils import logging
from .configuration_navil_vit import NaViLVisionConfig
from .configuration_internlm2 import InternLM2Config
logger = logging.get_logger(__name__)
class NaViLChatConfig(PretrainedConfig):
model_type = 'navil_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=-1,
force_image_size=None,
downsample_ratio=0.5,
template=None,
anyres_image_size=True,
scale_downsample_ratio=0.7071,
ps_version='v1',
min_dynamic_patch=256,
max_dynamic_patch=24576,
**kwargs):
super().__init__(**kwargs)
if vision_config is None:
vision_config = {}
logger.info('vision_config is None. Initializing the NaViLVisionConfig with default values.')
if llm_config is None:
llm_config = {'architectures': ['InternLM2VEForCausalLM']}
logger.info('llm_config is None. Initializing the llm_config with default values (`InternLM2VEForCausalLM`).')
self.vision_config = NaViLVisionConfig(**vision_config)
self.vision_config.downsample_ratio = downsample_ratio
if llm_config['architectures'][0] == 'InternLM2VEForCausalLM':
self.llm_config = InternLM2Config(**llm_config)
else:
raise ValueError('Unsupported architecture: {}'.format(llm_config['architectures'][0]))
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.anyres_image_size = anyres_image_size
self.scale_downsample_ratio = scale_downsample_ratio
self.ps_version = ps_version # pixel shuffle version
self.min_dynamic_patch = min_dynamic_patch
self.max_dynamic_patch = max_dynamic_patch
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['anyres_image_size'] = self.anyres_image_size
output['scale_downsample_ratio'] = self.scale_downsample_ratio
output['ps_version'] = self.ps_version
output['min_dynamic_patch'] = self.min_dynamic_patch
output['max_dynamic_patch'] = self.max_dynamic_patch
return output
|