File size: 1,037 Bytes
b92bd4e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 |
from typing import Any
from transformers.configuration_utils import PretrainedConfig
__all__ = ["VoRAConfig"]
class VoRAConfig(PretrainedConfig):
model_type = "vora"
_auto_class = "AutoConfig"
def __init__(
self,
llm: str = "",
aux_vision: str = "",
lora: dict = {},
image_size: int = 448,
vision_embedding_type: str = "",
vision_embedding_intermediate_size: int = 1536,
patch_size: int = 14,
vision_attention_mask: str = "bidirectional",
rms_norm_eps: float = 1e-5,
**kwargs: Any,
):
super().__init__(**kwargs)
self.llm = llm
self.aux_vision = aux_vision
self.lora = lora
self.image_size = image_size
self.vision_embedding_type = vision_embedding_type
self.vision_embedding_intermediate_size = vision_embedding_intermediate_size
self.patch_size = patch_size
self.vision_attention_mask = vision_attention_mask
self.rms_norm_eps = rms_norm_eps
|