|
from transformers import LlamaTokenizer |
|
|
|
class LlamaTokenizerWrapper(LlamaTokenizer): |
|
def __init__(self, **kwargs): |
|
super().__init__(**kwargs) |
|
self.im_start = "<image>" |
|
self.im_end = "</image>" |
|
self.ref_start = "<ref>" |
|
self.ref_end = "</ref>" |
|
self.box_start = "<box>" |
|
self.box_end = "</box>" |
|
self.quad_start = "<quad>" |
|
self.quad_end = "</quad>" |
|
self.point_start = "<point>" |
|
self.point_end = "</point>" |
|
self.slice_start = "<slice>" |
|
self.slice_end = "</slice>" |
|
|
|
@property |
|
def eos_id(self): |
|
return self.sp_model.eos_id() |
|
|
|
@property |
|
def bos_id(self): |
|
return self.sp_model.bos_id() |
|
|
|
@property |
|
def unk_id(self): |
|
return self.sp_model.unk_id() |
|
|
|
@property |
|
def im_start_id(self): |
|
return self._convert_token_to_id(self.im_start) |
|
|
|
@property |
|
def im_end_id(self): |
|
return self._convert_token_to_id(self.im_end) |
