[Model] Standardize common vision encoders (#31947)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2026-01-08 02:33:16 -08:00
committed by GitHub
parent d1b6fe007f
commit 5576227bc1
19 changed files with 253 additions and 173 deletions
@@ -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"),
)