Upload tokenizer
Browse files- special_tokens_map.json +0 -16
- tokenizer_config.json +34 -0
special_tokens_map.json
CHANGED
@@ -1,20 +1,4 @@
|
|
1 |
{
|
2 |
-
"additional_special_tokens": [
|
3 |
-
{
|
4 |
-
"content": "<s>",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": true,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false
|
9 |
-
},
|
10 |
-
{
|
11 |
-
"content": "</s>",
|
12 |
-
"lstrip": false,
|
13 |
-
"normalized": true,
|
14 |
-
"rstrip": false,
|
15 |
-
"single_word": false
|
16 |
-
}
|
17 |
-
],
|
18 |
"bos_token": "<s>",
|
19 |
"eos_token": "</s>",
|
20 |
"pad_token": "[PAD]",
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": "<s>",
|
3 |
"eos_token": "</s>",
|
4 |
"pad_token": "[PAD]",
|
tokenizer_config.json
CHANGED
@@ -1,4 +1,38 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": "<s>",
|
3 |
"clean_up_tokenization_spaces": true,
|
4 |
"do_lower_case": false,
|
|
|
1 |
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"139": {
|
4 |
+
"content": "[UNK]",
|
5 |
+
"lstrip": true,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": true,
|
8 |
+
"single_word": false,
|
9 |
+
"special": false
|
10 |
+
},
|
11 |
+
"140": {
|
12 |
+
"content": "[PAD]",
|
13 |
+
"lstrip": true,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": true,
|
16 |
+
"single_word": false,
|
17 |
+
"special": false
|
18 |
+
},
|
19 |
+
"141": {
|
20 |
+
"content": "<s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": true,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"142": {
|
28 |
+
"content": "</s>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
}
|
35 |
+
},
|
36 |
"bos_token": "<s>",
|
37 |
"clean_up_tokenization_spaces": true,
|
38 |
"do_lower_case": false,
|