Upload tokenizer.json
Browse filesUpdated tokenizer.json
- tokenizer.json +14 -25
tokenizer.json
CHANGED
|
@@ -1,64 +1,52 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
| 5 |
-
"max_length": 514,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
-
"padding": {
|
| 10 |
-
"strategy": "BatchLongest",
|
| 11 |
-
"direction": "Right",
|
| 12 |
-
"pad_to_multiple_of": null,
|
| 13 |
-
"pad_id": 1,
|
| 14 |
-
"pad_type_id": 0,
|
| 15 |
-
"pad_token": "<pad>"
|
| 16 |
-
},
|
| 17 |
"added_tokens": [
|
| 18 |
{
|
| 19 |
"id": 0,
|
|
|
|
| 20 |
"content": "<s>",
|
| 21 |
"single_word": false,
|
| 22 |
"lstrip": false,
|
| 23 |
"rstrip": false,
|
| 24 |
-
"normalized": false
|
| 25 |
-
"special": true
|
| 26 |
},
|
| 27 |
{
|
| 28 |
"id": 1,
|
|
|
|
| 29 |
"content": "<pad>",
|
| 30 |
"single_word": false,
|
| 31 |
"lstrip": false,
|
| 32 |
"rstrip": false,
|
| 33 |
-
"normalized": false
|
| 34 |
-
"special": true
|
| 35 |
},
|
| 36 |
{
|
| 37 |
"id": 2,
|
|
|
|
| 38 |
"content": "</s>",
|
| 39 |
"single_word": false,
|
| 40 |
"lstrip": false,
|
| 41 |
"rstrip": false,
|
| 42 |
-
"normalized": false
|
| 43 |
-
"special": true
|
| 44 |
},
|
| 45 |
{
|
| 46 |
"id": 3,
|
|
|
|
| 47 |
"content": "<unk>",
|
| 48 |
"single_word": false,
|
| 49 |
"lstrip": false,
|
| 50 |
"rstrip": false,
|
| 51 |
-
"normalized": false
|
| 52 |
-
"special": true
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"id": 128000,
|
|
|
|
| 56 |
"content": "<mask>",
|
| 57 |
"single_word": false,
|
| 58 |
"lstrip": true,
|
| 59 |
"rstrip": false,
|
| 60 |
-
"normalized": false
|
| 61 |
-
"special": true
|
| 62 |
}
|
| 63 |
],
|
| 64 |
"normalizer": {
|
|
@@ -67,7 +55,8 @@
|
|
| 67 |
"pre_tokenizer": {
|
| 68 |
"type": "Metaspace",
|
| 69 |
"replacement": "▁",
|
| 70 |
-
"add_prefix_space":
|
|
|
|
| 71 |
},
|
| 72 |
"post_processor": {
|
| 73 |
"type": "RobertaProcessing",
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
| 8 |
+
"special": true,
|
| 9 |
"content": "<s>",
|
| 10 |
"single_word": false,
|
| 11 |
"lstrip": false,
|
| 12 |
"rstrip": false,
|
| 13 |
+
"normalized": false
|
|
|
|
| 14 |
},
|
| 15 |
{
|
| 16 |
"id": 1,
|
| 17 |
+
"special": true,
|
| 18 |
"content": "<pad>",
|
| 19 |
"single_word": false,
|
| 20 |
"lstrip": false,
|
| 21 |
"rstrip": false,
|
| 22 |
+
"normalized": false
|
|
|
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"id": 2,
|
| 26 |
+
"special": true,
|
| 27 |
"content": "</s>",
|
| 28 |
"single_word": false,
|
| 29 |
"lstrip": false,
|
| 30 |
"rstrip": false,
|
| 31 |
+
"normalized": false
|
|
|
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"id": 3,
|
| 35 |
+
"special": true,
|
| 36 |
"content": "<unk>",
|
| 37 |
"single_word": false,
|
| 38 |
"lstrip": false,
|
| 39 |
"rstrip": false,
|
| 40 |
+
"normalized": false
|
|
|
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 128000,
|
| 44 |
+
"special": true,
|
| 45 |
"content": "<mask>",
|
| 46 |
"single_word": false,
|
| 47 |
"lstrip": true,
|
| 48 |
"rstrip": false,
|
| 49 |
+
"normalized": false
|
|
|
|
| 50 |
}
|
| 51 |
],
|
| 52 |
"normalizer": {
|
|
|
|
| 55 |
"pre_tokenizer": {
|
| 56 |
"type": "Metaspace",
|
| 57 |
"replacement": "▁",
|
| 58 |
+
"add_prefix_space": true,
|
| 59 |
+
"prepend_scheme": "never"
|
| 60 |
},
|
| 61 |
"post_processor": {
|
| 62 |
"type": "RobertaProcessing",
|