[Model] Broadcast Ovis2 implementation to fit Ovis1.6 (#17861)

Signed-off-by: Isotr0py <2037008807@qq.com>
This commit is contained in:
Isotr0py
2025-05-12 08:56:30 +08:00
committed by GitHub
parent 7de18d541b
commit 021c16c7ca
16 changed files with 330 additions and 212 deletions

View File

@@ -23,7 +23,7 @@ from vllm.transformers_utils.configs.moonvit import MoonViTConfig
from vllm.transformers_utils.configs.mpt import MPTConfig
from vllm.transformers_utils.configs.nemotron import NemotronConfig
from vllm.transformers_utils.configs.nvlm_d import NVLM_D_Config
from vllm.transformers_utils.configs.ovis2 import OvisConfig
from vllm.transformers_utils.configs.ovis import OvisConfig
from vllm.transformers_utils.configs.skyworkr1v import SkyworkR1VChatConfig
from vllm.transformers_utils.configs.solar import SolarConfig
from vllm.transformers_utils.configs.telechat2 import Telechat2Config

View File

@@ -123,6 +123,19 @@ class Aimv2VisualTokenizerConfig(BaseVisualTokenizerConfig):
self.backbone_kwargs['num_hidden_layers'] = self.depths[0]
class SiglipVisualTokenizerConfig(BaseVisualTokenizerConfig):
model_type = "siglip_visual_tokenizer"
def __init__(self, **kwargs):
super().__init__(**kwargs)
if self.drop_cls_token:
self.drop_cls_token = False
if self.depths:
assert len(self.depths) == 1
self.backbone_kwargs['num_hidden_layers'] = self.depths[0]
AutoConfig.register("siglip_visual_tokenizer", SiglipVisualTokenizerConfig)
AutoConfig.register("aimv2_visual_tokenizer", Aimv2VisualTokenizerConfig)