[Core] Move multimodal placeholder from chat utils to model definition (#20355)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
@@ -735,6 +735,15 @@ class MiniCPMVBaseModel(nn.Module, SupportsMultiModal, SupportsPP):
|
||||
instantiated.
|
||||
"""
|
||||
|
||||
@classmethod
|
||||
def get_placeholder_str(cls, modality: str, i: int) -> Optional[str]:
|
||||
if modality.startswith("image"):
|
||||
return "(<image>./</image>)"
|
||||
if modality.startswith("video"):
|
||||
return "(<video>./</video>)"
|
||||
|
||||
raise ValueError("Only image or video modality is supported")
|
||||
|
||||
def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):
|
||||
config = vllm_config.model_config.hf_config
|
||||
multimodal_config = vllm_config.model_config.multimodal_config
|
||||
|
||||
Reference in New Issue
Block a user