Upload tokenizer
Browse files- tokenizer.json +18 -4
- tokenizer_config.json +1 -1
tokenizer.json
CHANGED
|
@@ -1,7 +1,21 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
|
@@ -70,7 +84,7 @@
|
|
| 70 |
"normalizer": null,
|
| 71 |
"pre_tokenizer": {
|
| 72 |
"type": "ByteLevel",
|
| 73 |
-
"add_prefix_space":
|
| 74 |
"trim_offsets": true,
|
| 75 |
"use_regex": true
|
| 76 |
},
|
|
@@ -85,7 +99,7 @@
|
|
| 85 |
0
|
| 86 |
],
|
| 87 |
"trim_offsets": true,
|
| 88 |
-
"add_prefix_space":
|
| 89 |
},
|
| 90 |
"decoder": {
|
| 91 |
"type": "ByteLevel",
|
|
|
|
| 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,
|
|
|
|
| 84 |
"normalizer": null,
|
| 85 |
"pre_tokenizer": {
|
| 86 |
"type": "ByteLevel",
|
| 87 |
+
"add_prefix_space": true,
|
| 88 |
"trim_offsets": true,
|
| 89 |
"use_regex": true
|
| 90 |
},
|
|
|
|
| 99 |
0
|
| 100 |
],
|
| 101 |
"trim_offsets": true,
|
| 102 |
+
"add_prefix_space": true
|
| 103 |
},
|
| 104 |
"decoder": {
|
| 105 |
"type": "ByteLevel",
|
tokenizer_config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"add_prefix_space":
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"0": {
|
| 5 |
"content": "<s>",
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"0": {
|
| 5 |
"content": "<s>",
|