[Models]: Make Multimodal config implicit in ViT implementation (#31972)

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
This commit is contained in:
Isotr0py
2026-01-24 20:34:26 +08:00
committed by GitHub
parent 6450b536a6
commit 9ad7f89f55
38 changed files with 118 additions and 470 deletions
@@ -398,7 +398,6 @@ class DeepseekOCRForCausalLM(nn.Module, SupportsMultiModal, SupportsPP, Supports
self.vision_model = DeepCLIPVisionTransformer(
config=clip_vision_config,
quant_config=quant_config,
multimodal_config=multimodal_config,
prefix=maybe_prefix(prefix, "vision_model"),
)