Commit
•
7ce0ddc
1
Parent(s):
b0586cd
Upload tokenizer
Browse files- special_tokens_map.json +4 -1
- tokenizer.json +20 -1
- tokenizer_config.json +21 -2
special_tokens_map.json
CHANGED
|
@@ -1 +1,4 @@
|
|
| 1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pad_token": "[PAD]",
|
| 3 |
+
"unk_token": "[UNK]"
|
| 4 |
+
}
|
tokenizer.json
CHANGED
|
@@ -2,7 +2,26 @@
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": null,
|
| 4 |
"padding": null,
|
| 5 |
-
"added_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"normalizer": null,
|
| 7 |
"pre_tokenizer": {
|
| 8 |
"type": "Whitespace"
|
|
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": null,
|
| 4 |
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 50000,
|
| 8 |
+
"content": "[UNK]",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 50001,
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
}
|
| 24 |
+
],
|
| 25 |
"normalizer": null,
|
| 26 |
"pre_tokenizer": {
|
| 27 |
"type": "Whitespace"
|
tokenizer_config.json
CHANGED
|
@@ -1,6 +1,25 @@
|
|
| 1 |
{
|
| 2 |
-
"added_tokens_decoder": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"clean_up_tokenization_spaces": true,
|
| 4 |
"model_max_length": 1000000000000000019884624838656,
|
| 5 |
-
"
|
|
|
|
|
|
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"50000": {
|
| 4 |
+
"content": "[UNK]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"50001": {
|
| 12 |
+
"content": "[PAD]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
}
|
| 19 |
+
},
|
| 20 |
"clean_up_tokenization_spaces": true,
|
| 21 |
"model_max_length": 1000000000000000019884624838656,
|
| 22 |
+
"pad_token": "[PAD]",
|
| 23 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 24 |
+
"unk_token": "[UNK]"
|
| 25 |
}
|