[Model] Standardize common vision encoders (#31947)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
@@ -397,6 +397,7 @@ 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