[Models]: Make Multimodal config implicit in ViT implementation (#31972)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
This commit is contained in:
@@ -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"),
|
||||
)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user