Upload tokenizer
Browse files- added_tokens.json +2 -2
- special_tokens_map.json +2 -2
- tokenizer.json +0 -0
- tokenizer_config.json +7 -7
- vocab.txt +0 -0
added_tokens.json
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"[
|
| 3 |
-
"[
|
| 4 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"[END]": 28997,
|
| 3 |
+
"[START]": 28996
|
| 4 |
}
|
special_tokens_map.json
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
{
|
| 4 |
-
"content": "[
|
| 5 |
"lstrip": false,
|
| 6 |
"normalized": false,
|
| 7 |
"rstrip": false,
|
| 8 |
"single_word": false
|
| 9 |
},
|
| 10 |
{
|
| 11 |
-
"content": "[
|
| 12 |
"lstrip": false,
|
| 13 |
"normalized": false,
|
| 14 |
"rstrip": false,
|
|
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
{
|
| 4 |
+
"content": "[START]",
|
| 5 |
"lstrip": false,
|
| 6 |
"normalized": false,
|
| 7 |
"rstrip": false,
|
| 8 |
"single_word": false
|
| 9 |
},
|
| 10 |
{
|
| 11 |
+
"content": "[END]",
|
| 12 |
"lstrip": false,
|
| 13 |
"normalized": false,
|
| 14 |
"rstrip": false,
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -40,16 +40,16 @@
|
|
| 40 |
"single_word": false,
|
| 41 |
"special": true
|
| 42 |
},
|
| 43 |
-
"
|
| 44 |
-
"content": "[
|
| 45 |
"lstrip": false,
|
| 46 |
"normalized": false,
|
| 47 |
"rstrip": false,
|
| 48 |
"single_word": false,
|
| 49 |
"special": true
|
| 50 |
},
|
| 51 |
-
"
|
| 52 |
-
"content": "[
|
| 53 |
"lstrip": false,
|
| 54 |
"normalized": false,
|
| 55 |
"rstrip": false,
|
|
@@ -58,10 +58,10 @@
|
|
| 58 |
}
|
| 59 |
},
|
| 60 |
"additional_special_tokens": [
|
| 61 |
-
"[
|
| 62 |
-
"[
|
| 63 |
],
|
| 64 |
-
"clean_up_tokenization_spaces":
|
| 65 |
"cls_token": "[CLS]",
|
| 66 |
"do_lower_case": false,
|
| 67 |
"mask_token": "[MASK]",
|
|
|
|
| 40 |
"single_word": false,
|
| 41 |
"special": true
|
| 42 |
},
|
| 43 |
+
"28996": {
|
| 44 |
+
"content": "[START]",
|
| 45 |
"lstrip": false,
|
| 46 |
"normalized": false,
|
| 47 |
"rstrip": false,
|
| 48 |
"single_word": false,
|
| 49 |
"special": true
|
| 50 |
},
|
| 51 |
+
"28997": {
|
| 52 |
+
"content": "[END]",
|
| 53 |
"lstrip": false,
|
| 54 |
"normalized": false,
|
| 55 |
"rstrip": false,
|
|
|
|
| 58 |
}
|
| 59 |
},
|
| 60 |
"additional_special_tokens": [
|
| 61 |
+
"[START]",
|
| 62 |
+
"[END]"
|
| 63 |
],
|
| 64 |
+
"clean_up_tokenization_spaces": false,
|
| 65 |
"cls_token": "[CLS]",
|
| 66 |
"do_lower_case": false,
|
| 67 |
"mask_token": "[MASK]",
|
vocab.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|