Update tokenization_chatglm.py
#100
by
puffy310
- opened
- tokenization_chatglm.py +1 -2
tokenization_chatglm.py
CHANGED
@@ -193,6 +193,7 @@ class ChatGLMTokenizer(PreTrainedTokenizer):
|
|
193 |
num_image_tokens=20000,
|
194 |
**kwargs
|
195 |
) -> None:
|
|
|
196 |
super().__init__(
|
197 |
do_lower_case=do_lower_case,
|
198 |
remove_space=remove_space,
|
@@ -218,8 +219,6 @@ class ChatGLMTokenizer(PreTrainedTokenizer):
|
|
218 |
self.mask_token = mask_token
|
219 |
self.gmask_token = gmask_token
|
220 |
|
221 |
-
self.sp_tokenizer = SPTokenizer(vocab_file, num_image_tokens=num_image_tokens)
|
222 |
-
|
223 |
""" Initialisation """
|
224 |
|
225 |
@property
|
|
|
193 |
num_image_tokens=20000,
|
194 |
**kwargs
|
195 |
) -> None:
|
196 |
+
self.sp_tokenizer = SPTokenizer(vocab_file, num_image_tokens=num_image_tokens)
|
197 |
super().__init__(
|
198 |
do_lower_case=do_lower_case,
|
199 |
remove_space=remove_space,
|
|
|
219 |
self.mask_token = mask_token
|
220 |
self.gmask_token = gmask_token
|
221 |
|
|
|
|
|
222 |
""" Initialisation """
|
223 |
|
224 |
@property
|