[Models]: Make Multimodal config implicit in ViT implementation (#31972)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
This commit is contained in:
@@ -166,7 +166,6 @@ class LightOnOCRForConditionalGeneration(Mistral3ForConditionalGeneration):
|
||||
self.vision_tower = init_vision_tower_for_llava(
|
||||
config,
|
||||
quant_config=quant_config,
|
||||
multimodal_config=multimodal_config,
|
||||
require_post_norm=False,
|
||||
prefix=maybe_prefix(prefix, "vision_tower"),
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user