Upload tokenizer
Browse files- tokenizer.json +20 -4
tokenizer.json
CHANGED
|
@@ -1,7 +1,21 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
|
@@ -89,7 +103,8 @@
|
|
| 89 |
{
|
| 90 |
"type": "Metaspace",
|
| 91 |
"replacement": "▁",
|
| 92 |
-
"add_prefix_space": true
|
|
|
|
| 93 |
}
|
| 94 |
]
|
| 95 |
},
|
|
@@ -177,7 +192,8 @@
|
|
| 177 |
"decoder": {
|
| 178 |
"type": "Metaspace",
|
| 179 |
"replacement": "▁",
|
| 180 |
-
"add_prefix_space": true
|
|
|
|
| 181 |
},
|
| 182 |
"model": {
|
| 183 |
"type": "Unigram",
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 512,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": {
|
| 10 |
+
"strategy": {
|
| 11 |
+
"Fixed": 512
|
| 12 |
+
},
|
| 13 |
+
"direction": "Right",
|
| 14 |
+
"pad_to_multiple_of": null,
|
| 15 |
+
"pad_id": 1,
|
| 16 |
+
"pad_type_id": 0,
|
| 17 |
+
"pad_token": "<pad>"
|
| 18 |
+
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
|
|
|
| 103 |
{
|
| 104 |
"type": "Metaspace",
|
| 105 |
"replacement": "▁",
|
| 106 |
+
"add_prefix_space": true,
|
| 107 |
+
"prepend_scheme": "always"
|
| 108 |
}
|
| 109 |
]
|
| 110 |
},
|
|
|
|
| 192 |
"decoder": {
|
| 193 |
"type": "Metaspace",
|
| 194 |
"replacement": "▁",
|
| 195 |
+
"add_prefix_space": true,
|
| 196 |
+
"prepend_scheme": "always"
|
| 197 |
},
|
| 198 |
"model": {
|
| 199 |
"type": "Unigram",
|