Commit
•
c5a9cc5
1
Parent(s):
45b2acb
Upload tokenizer
Browse files- special_tokens_map.json +6 -6
- tokenizer.json +4 -4
- tokenizer_config.json +4 -4
special_tokens_map.json
CHANGED
|
@@ -2,21 +2,21 @@
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "<s>",
|
| 4 |
"lstrip": false,
|
| 5 |
-
"normalized":
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"cls_token": {
|
| 10 |
"content": "<s>",
|
| 11 |
"lstrip": false,
|
| 12 |
-
"normalized":
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"eos_token": {
|
| 17 |
"content": "</s>",
|
| 18 |
"lstrip": false,
|
| 19 |
-
"normalized":
|
| 20 |
"rstrip": false,
|
| 21 |
"single_word": false
|
| 22 |
},
|
|
@@ -30,21 +30,21 @@
|
|
| 30 |
"pad_token": {
|
| 31 |
"content": "<pad>",
|
| 32 |
"lstrip": false,
|
| 33 |
-
"normalized":
|
| 34 |
"rstrip": false,
|
| 35 |
"single_word": false
|
| 36 |
},
|
| 37 |
"sep_token": {
|
| 38 |
"content": "</s>",
|
| 39 |
"lstrip": false,
|
| 40 |
-
"normalized":
|
| 41 |
"rstrip": false,
|
| 42 |
"single_word": false
|
| 43 |
},
|
| 44 |
"unk_token": {
|
| 45 |
"content": "<unk>",
|
| 46 |
"lstrip": false,
|
| 47 |
-
"normalized":
|
| 48 |
"rstrip": false,
|
| 49 |
"single_word": false
|
| 50 |
}
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "<s>",
|
| 4 |
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"cls_token": {
|
| 10 |
"content": "<s>",
|
| 11 |
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"eos_token": {
|
| 17 |
"content": "</s>",
|
| 18 |
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
"rstrip": false,
|
| 21 |
"single_word": false
|
| 22 |
},
|
|
|
|
| 30 |
"pad_token": {
|
| 31 |
"content": "<pad>",
|
| 32 |
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
"rstrip": false,
|
| 35 |
"single_word": false
|
| 36 |
},
|
| 37 |
"sep_token": {
|
| 38 |
"content": "</s>",
|
| 39 |
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
"rstrip": false,
|
| 42 |
"single_word": false
|
| 43 |
},
|
| 44 |
"unk_token": {
|
| 45 |
"content": "<unk>",
|
| 46 |
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
"rstrip": false,
|
| 49 |
"single_word": false
|
| 50 |
}
|
tokenizer.json
CHANGED
|
@@ -9,7 +9,7 @@
|
|
| 9 |
"single_word": false,
|
| 10 |
"lstrip": false,
|
| 11 |
"rstrip": false,
|
| 12 |
-
"normalized":
|
| 13 |
"special": true
|
| 14 |
},
|
| 15 |
{
|
|
@@ -18,7 +18,7 @@
|
|
| 18 |
"single_word": false,
|
| 19 |
"lstrip": false,
|
| 20 |
"rstrip": false,
|
| 21 |
-
"normalized":
|
| 22 |
"special": true
|
| 23 |
},
|
| 24 |
{
|
|
@@ -27,7 +27,7 @@
|
|
| 27 |
"single_word": false,
|
| 28 |
"lstrip": false,
|
| 29 |
"rstrip": false,
|
| 30 |
-
"normalized":
|
| 31 |
"special": true
|
| 32 |
},
|
| 33 |
{
|
|
@@ -36,7 +36,7 @@
|
|
| 36 |
"single_word": false,
|
| 37 |
"lstrip": false,
|
| 38 |
"rstrip": false,
|
| 39 |
-
"normalized":
|
| 40 |
"special": true
|
| 41 |
},
|
| 42 |
{
|
|
|
|
| 9 |
"single_word": false,
|
| 10 |
"lstrip": false,
|
| 11 |
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
"special": true
|
| 14 |
},
|
| 15 |
{
|
|
|
|
| 18 |
"single_word": false,
|
| 19 |
"lstrip": false,
|
| 20 |
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
"special": true
|
| 23 |
},
|
| 24 |
{
|
|
|
|
| 27 |
"single_word": false,
|
| 28 |
"lstrip": false,
|
| 29 |
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
"special": true
|
| 32 |
},
|
| 33 |
{
|
|
|
|
| 36 |
"single_word": false,
|
| 37 |
"lstrip": false,
|
| 38 |
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
"special": true
|
| 41 |
},
|
| 42 |
{
|
tokenizer_config.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
"0": {
|
| 5 |
"content": "<s>",
|
| 6 |
"lstrip": false,
|
| 7 |
-
"normalized":
|
| 8 |
"rstrip": false,
|
| 9 |
"single_word": false,
|
| 10 |
"special": true
|
|
@@ -12,7 +12,7 @@
|
|
| 12 |
"1": {
|
| 13 |
"content": "<pad>",
|
| 14 |
"lstrip": false,
|
| 15 |
-
"normalized":
|
| 16 |
"rstrip": false,
|
| 17 |
"single_word": false,
|
| 18 |
"special": true
|
|
@@ -20,7 +20,7 @@
|
|
| 20 |
"2": {
|
| 21 |
"content": "</s>",
|
| 22 |
"lstrip": false,
|
| 23 |
-
"normalized":
|
| 24 |
"rstrip": false,
|
| 25 |
"single_word": false,
|
| 26 |
"special": true
|
|
@@ -28,7 +28,7 @@
|
|
| 28 |
"3": {
|
| 29 |
"content": "<unk>",
|
| 30 |
"lstrip": false,
|
| 31 |
-
"normalized":
|
| 32 |
"rstrip": false,
|
| 33 |
"single_word": false,
|
| 34 |
"special": true
|
|
|
|
| 4 |
"0": {
|
| 5 |
"content": "<s>",
|
| 6 |
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
"rstrip": false,
|
| 9 |
"single_word": false,
|
| 10 |
"special": true
|
|
|
|
| 12 |
"1": {
|
| 13 |
"content": "<pad>",
|
| 14 |
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
"rstrip": false,
|
| 17 |
"single_word": false,
|
| 18 |
"special": true
|
|
|
|
| 20 |
"2": {
|
| 21 |
"content": "</s>",
|
| 22 |
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
"rstrip": false,
|
| 25 |
"single_word": false,
|
| 26 |
"special": true
|
|
|
|
| 28 |
"3": {
|
| 29 |
"content": "<unk>",
|
| 30 |
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
"rstrip": false,
|
| 33 |
"single_word": false,
|
| 34 |
"special": true
|