Fix comments

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
This commit is contained in:
Jee Jee Li 2025-12-12 00:05:07 +00:00
parent e10321bf6a
commit 208dc0c954

View File

@ -56,8 +56,10 @@ class LoRAConfig:
will be automatically assigned to 1-n with the names of the modalities will be automatically assigned to 1-n with the names of the modalities
in alphabetic order.""" in alphabetic order."""
enable_tower_connector_lora: bool = False enable_tower_connector_lora: bool = False
"""If `True`, LoRA support for multimodal models will be enabled. Currently, """If `True`, LoRA support for the tower (vision encoder) and connector
only the qwenvl series models support this feature. The default is False.""" of multimodal models will be enabled. This is an experimental feature and
currently only supports some MM models such as the Qwen VL series. The default
is False."""
def compute_hash(self) -> str: def compute_hash(self) -> str:
""" """