Commit
•
b24155f
1
Parent(s):
45f0718
Update tokenization_baichuan.py
Browse files- tokenization_baichuan.py +7 -5
tokenization_baichuan.py
CHANGED
@@ -72,6 +72,13 @@ class BaichuanTokenizer(PreTrainedTokenizer):
|
|
72 |
eos_token = AddedToken(eos_token, lstrip=False, rstrip=False) if isinstance(eos_token, str) else eos_token
|
73 |
unk_token = AddedToken(unk_token, lstrip=False, rstrip=False) if isinstance(unk_token, str) else unk_token
|
74 |
pad_token = AddedToken(pad_token, lstrip=False, rstrip=False) if isinstance(pad_token, str) else pad_token
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
75 |
super().__init__(
|
76 |
bos_token=bos_token,
|
77 |
eos_token=eos_token,
|
@@ -83,11 +90,6 @@ class BaichuanTokenizer(PreTrainedTokenizer):
|
|
83 |
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
|
84 |
**kwargs,
|
85 |
)
|
86 |
-
self.vocab_file = vocab_file
|
87 |
-
self.add_bos_token = add_bos_token
|
88 |
-
self.add_eos_token = add_eos_token
|
89 |
-
self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
|
90 |
-
self.sp_model.Load(vocab_file)
|
91 |
|
92 |
def __getstate__(self):
|
93 |
state = self.__dict__.copy()
|
|
|
72 |
eos_token = AddedToken(eos_token, lstrip=False, rstrip=False) if isinstance(eos_token, str) else eos_token
|
73 |
unk_token = AddedToken(unk_token, lstrip=False, rstrip=False) if isinstance(unk_token, str) else unk_token
|
74 |
pad_token = AddedToken(pad_token, lstrip=False, rstrip=False) if isinstance(pad_token, str) else pad_token
|
75 |
+
|
76 |
+
self.vocab_file = vocab_file
|
77 |
+
self.add_bos_token = add_bos_token
|
78 |
+
self.add_eos_token = add_eos_token
|
79 |
+
self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
|
80 |
+
self.sp_model.Load(vocab_file)
|
81 |
+
|
82 |
super().__init__(
|
83 |
bos_token=bos_token,
|
84 |
eos_token=eos_token,
|
|
|
90 |
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
|
91 |
**kwargs,
|
92 |
)
|
|
|
|
|
|
|
|
|
|
|
93 |
|
94 |
def __getstate__(self):
|
95 |
state = self.__dict__.copy()
|