KhimNguyen
commited on
Commit
•
a484ee9
1
Parent(s):
6ef3535
Config
Browse files- special_tokens_map.json +42 -6
- tokenizer.json +0 -0
- tokenizer_config.json +7 -0
special_tokens_map.json
CHANGED
@@ -3,9 +3,27 @@
|
|
3 |
"<s_iitcdip>",
|
4 |
"<s_synthdog>"
|
5 |
],
|
6 |
-
"bos_token":
|
7 |
-
|
8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
"mask_token": {
|
10 |
"content": "<mask>",
|
11 |
"lstrip": true,
|
@@ -13,7 +31,25 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token":
|
17 |
-
|
18 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
}
|
|
|
3 |
"<s_iitcdip>",
|
4 |
"<s_synthdog>"
|
5 |
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<s>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"cls_token": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"eos_token": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
"mask_token": {
|
28 |
"content": "<mask>",
|
29 |
"lstrip": true,
|
|
|
31 |
"rstrip": false,
|
32 |
"single_word": false
|
33 |
},
|
34 |
+
"pad_token": {
|
35 |
+
"content": "<pad>",
|
36 |
+
"lstrip": false,
|
37 |
+
"normalized": false,
|
38 |
+
"rstrip": false,
|
39 |
+
"single_word": false
|
40 |
+
},
|
41 |
+
"sep_token": {
|
42 |
+
"content": "</s>",
|
43 |
+
"lstrip": false,
|
44 |
+
"normalized": false,
|
45 |
+
"rstrip": false,
|
46 |
+
"single_word": false
|
47 |
+
},
|
48 |
+
"unk_token": {
|
49 |
+
"content": "<unk>",
|
50 |
+
"lstrip": false,
|
51 |
+
"normalized": false,
|
52 |
+
"rstrip": false,
|
53 |
+
"single_word": false
|
54 |
+
}
|
55 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -178,11 +178,18 @@
|
|
178 |
"cls_token": "<s>",
|
179 |
"eos_token": "</s>",
|
180 |
"mask_token": "<mask>",
|
|
|
181 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
182 |
"pad_token": "<pad>",
|
|
|
|
|
183 |
"processor_class": "DonutProcessor",
|
184 |
"sep_token": "</s>",
|
185 |
"sp_model_kwargs": {},
|
|
|
186 |
"tokenizer_class": "XLMRobertaTokenizer",
|
|
|
|
|
187 |
"unk_token": "<unk>"
|
188 |
}
|
|
|
178 |
"cls_token": "<s>",
|
179 |
"eos_token": "</s>",
|
180 |
"mask_token": "<mask>",
|
181 |
+
"max_length": 768,
|
182 |
"model_max_length": 1000000000000000019884624838656,
|
183 |
+
"pad_to_multiple_of": null,
|
184 |
"pad_token": "<pad>",
|
185 |
+
"pad_token_type_id": 0,
|
186 |
+
"padding_side": "right",
|
187 |
"processor_class": "DonutProcessor",
|
188 |
"sep_token": "</s>",
|
189 |
"sp_model_kwargs": {},
|
190 |
+
"stride": 0,
|
191 |
"tokenizer_class": "XLMRobertaTokenizer",
|
192 |
+
"truncation_side": "right",
|
193 |
+
"truncation_strategy": "longest_first",
|
194 |
"unk_token": "<unk>"
|
195 |
}
|