Update tokenization_chatglm.py
#3
by
ksuriuri
- opened
- tokenization_chatglm.py +5 -3
tokenization_chatglm.py
CHANGED
@@ -62,14 +62,16 @@ class ChatGLM4Tokenizer(PreTrainedTokenizer):
|
|
62 |
vocab = {self._convert_id_to_token(i): i for i in range(self.vocab_size)}
|
63 |
vocab.update(self.added_tokens_encoder)
|
64 |
return vocab
|
65 |
-
|
66 |
-
def convert_tokens_to_string(self, tokens: List[Union[bytes, str]]) -> str:
|
67 |
"""
|
68 |
Converts a sequence of tokens in a single string.
|
69 |
"""
|
70 |
text = ""
|
71 |
temp = b""
|
72 |
for t in tokens:
|
|
|
|
|
73 |
if isinstance(t, str):
|
74 |
if temp:
|
75 |
text += temp.decode("utf-8", errors="replace")
|
@@ -78,7 +80,7 @@ class ChatGLM4Tokenizer(PreTrainedTokenizer):
|
|
78 |
elif isinstance(t, bytes):
|
79 |
temp += t
|
80 |
else:
|
81 |
-
raise TypeError("token should only be of type
|
82 |
if temp:
|
83 |
text += temp.decode("utf-8", errors="replace")
|
84 |
return text
|
|
|
62 |
vocab = {self._convert_id_to_token(i): i for i in range(self.vocab_size)}
|
63 |
vocab.update(self.added_tokens_encoder)
|
64 |
return vocab
|
65 |
+
|
66 |
+
def convert_tokens_to_string(self, tokens: List[Union[bytes, str, int]]) -> str:
|
67 |
"""
|
68 |
Converts a sequence of tokens in a single string.
|
69 |
"""
|
70 |
text = ""
|
71 |
temp = b""
|
72 |
for t in tokens:
|
73 |
+
if isinstance(t, int):
|
74 |
+
t = chr(t)
|
75 |
if isinstance(t, str):
|
76 |
if temp:
|
77 |
text += temp.decode("utf-8", errors="replace")
|
|
|
80 |
elif isinstance(t, bytes):
|
81 |
temp += t
|
82 |
else:
|
83 |
+
raise TypeError("token should only be of type int, bytes or str")
|
84 |
if temp:
|
85 |
text += temp.decode("utf-8", errors="replace")
|
86 |
return text
|