File size: 1,659 Bytes
b5dc5e3 |
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 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 |
from transformers.models.qwen2 import Qwen2TokenizerFast
class MiniCPMVTokenizerFast(Qwen2TokenizerFast):
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.slice_start = "<slice>"
self.slice_end = "</slice>"
self.im_id_start = "<image_id>"
self.im_id_end = "</image_id>"
@property
def eos_id(self):
return self.eos_token_id
@property
def bos_id(self):
return self.bos_token_id
@property
def unk_id(self):
return self.unk_token_id
@property
def im_start_id(self):
return self.convert_tokens_to_ids(self.im_start)
@property
def im_end_id(self):
return self.convert_tokens_to_ids(self.im_end)
@property
def slice_start_id(self):
return self.convert_tokens_to_ids(self.slice_start)
@property
def slice_end_id(self):
return self.convert_tokens_to_ids(self.slice_end)
@property
def im_id_start_id(self):
return self.convert_tokens_to_ids(self.im_id_start)
@property
def im_id_end_id(self):
return self.convert_tokens_to_ids(self.im_id_end)
@property
def newline_id(self):
return self.convert_tokens_to_ids('\n')
@staticmethod
def escape(text: str) -> str:
return text
@staticmethod
def unescape(text: str) -> str:
return text |