kushaltatariya
commited on
Commit
•
cc4abc0
1
Parent(s):
b694cc1
Upload config
Browse files- special_tokens_map.json +49 -7
- tokenizer.json +1 -1
- tokenizer_config.json +2 -2
special_tokens_map.json
CHANGED
@@ -1,9 +1,51 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "[BOS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "[CLS]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "[EOS]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "[MASK]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "[PAD]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "[SEP]",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "[UNK]",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
}
|
tokenizer.json
CHANGED
@@ -64,7 +64,7 @@
|
|
64 |
"lstrip": false,
|
65 |
"rstrip": false,
|
66 |
"normalized": false,
|
67 |
-
"special":
|
68 |
}
|
69 |
],
|
70 |
"normalizer": {
|
|
|
64 |
"lstrip": false,
|
65 |
"rstrip": false,
|
66 |
"normalized": false,
|
67 |
+
"special": true
|
68 |
}
|
69 |
],
|
70 |
"normalizer": {
|
tokenizer_config.json
CHANGED
@@ -57,7 +57,7 @@
|
|
57 |
"normalized": false,
|
58 |
"rstrip": false,
|
59 |
"single_word": false,
|
60 |
-
"special":
|
61 |
}
|
62 |
},
|
63 |
"bos_token": "[BOS]",
|
@@ -77,7 +77,7 @@
|
|
77 |
"sep_token_id": 5,
|
78 |
"sp_model_kwargs": {},
|
79 |
"spaces_between_special_tokens": false,
|
80 |
-
"tokenizer_class": "
|
81 |
"unk_token": "[UNK]",
|
82 |
"unk_token_id": 1
|
83 |
}
|
|
|
57 |
"normalized": false,
|
58 |
"rstrip": false,
|
59 |
"single_word": false,
|
60 |
+
"special": true
|
61 |
}
|
62 |
},
|
63 |
"bos_token": "[BOS]",
|
|
|
77 |
"sep_token_id": 5,
|
78 |
"sp_model_kwargs": {},
|
79 |
"spaces_between_special_tokens": false,
|
80 |
+
"tokenizer_class": "HfTokenizerFromConfig",
|
81 |
"unk_token": "[UNK]",
|
82 |
"unk_token_id": 1
|
83 |
}
|