dheerajpai
commited on
Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer.json +9 -0
- tokenizer_config.json +9 -0
special_tokens_map.json
CHANGED
@@ -5,5 +5,12 @@
|
|
5 |
"normalized": false,
|
6 |
"rstrip": false,
|
7 |
"single_word": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
}
|
9 |
}
|
|
|
5 |
"normalized": false,
|
6 |
"rstrip": false,
|
7 |
"single_word": false
|
8 |
+
},
|
9 |
+
"pad_token": {
|
10 |
+
"content": "[PAD]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
}
|
16 |
}
|
tokenizer.json
CHANGED
@@ -3,6 +3,15 @@
|
|
3 |
"truncation": null,
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
{
|
7 |
"id": 4,
|
8 |
"content": "[MASK]",
|
|
|
3 |
"truncation": null,
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
+
{
|
7 |
+
"id": 0,
|
8 |
+
"content": "[PAD]",
|
9 |
+
"single_word": false,
|
10 |
+
"lstrip": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"special": true
|
14 |
+
},
|
15 |
{
|
16 |
"id": 4,
|
17 |
"content": "[MASK]",
|
tokenizer_config.json
CHANGED
@@ -1,5 +1,13 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"4": {
|
4 |
"content": "[MASK]",
|
5 |
"lstrip": false,
|
@@ -12,5 +20,6 @@
|
|
12 |
"clean_up_tokenization_spaces": true,
|
13 |
"mask_token": "[MASK]",
|
14 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
15 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
16 |
}
|
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
"4": {
|
12 |
"content": "[MASK]",
|
13 |
"lstrip": false,
|
|
|
20 |
"clean_up_tokenization_spaces": true,
|
21 |
"mask_token": "[MASK]",
|
22 |
"model_max_length": 1000000000000000019884624838656,
|
23 |
+
"pad_token": "[PAD]",
|
24 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
25 |
}
|