Upload folder using huggingface_hub
Browse files- tokenizer.json +12 -12
- tokenizer_config.json +6 -12
tokenizer.json
CHANGED
|
@@ -4,58 +4,58 @@
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
|
|
|
| 7 |
"content": "PAD",
|
| 8 |
"single_word": false,
|
| 9 |
"lstrip": false,
|
| 10 |
"rstrip": false,
|
| 11 |
"normalized": false,
|
| 12 |
-
"special": true
|
| 13 |
-
"id": 0
|
| 14 |
},
|
| 15 |
{
|
|
|
|
| 16 |
"content": "UNK__",
|
| 17 |
"single_word": false,
|
| 18 |
"lstrip": false,
|
| 19 |
"rstrip": false,
|
| 20 |
"normalized": false,
|
| 21 |
-
"special": true
|
| 22 |
-
"id": 1
|
| 23 |
},
|
| 24 |
{
|
|
|
|
| 25 |
"content": "UNK",
|
| 26 |
"single_word": false,
|
| 27 |
"lstrip": false,
|
| 28 |
"rstrip": false,
|
| 29 |
"normalized": false,
|
| 30 |
-
"special": true
|
| 31 |
-
"id": 2
|
| 32 |
},
|
| 33 |
{
|
|
|
|
| 34 |
"content": "MASK",
|
| 35 |
"single_word": false,
|
| 36 |
"lstrip": false,
|
| 37 |
"rstrip": false,
|
| 38 |
"normalized": false,
|
| 39 |
-
"special": true
|
| 40 |
-
"id": 3
|
| 41 |
},
|
| 42 |
{
|
|
|
|
| 43 |
"content": "BOS",
|
| 44 |
"single_word": false,
|
| 45 |
"lstrip": false,
|
| 46 |
"rstrip": false,
|
| 47 |
"normalized": false,
|
| 48 |
-
"special": true
|
| 49 |
-
"id": 4
|
| 50 |
},
|
| 51 |
{
|
|
|
|
| 52 |
"content": "EOS",
|
| 53 |
"single_word": false,
|
| 54 |
"lstrip": false,
|
| 55 |
"rstrip": false,
|
| 56 |
"normalized": false,
|
| 57 |
-
"special": true
|
| 58 |
-
"id": 5
|
| 59 |
}
|
| 60 |
],
|
| 61 |
"normalizer": null,
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
+
"id": 0,
|
| 8 |
"content": "PAD",
|
| 9 |
"single_word": false,
|
| 10 |
"lstrip": false,
|
| 11 |
"rstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
+
"special": true
|
|
|
|
| 14 |
},
|
| 15 |
{
|
| 16 |
+
"id": 1,
|
| 17 |
"content": "UNK__",
|
| 18 |
"single_word": false,
|
| 19 |
"lstrip": false,
|
| 20 |
"rstrip": false,
|
| 21 |
"normalized": false,
|
| 22 |
+
"special": true
|
|
|
|
| 23 |
},
|
| 24 |
{
|
| 25 |
+
"id": 2,
|
| 26 |
"content": "UNK",
|
| 27 |
"single_word": false,
|
| 28 |
"lstrip": false,
|
| 29 |
"rstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
+
"special": true
|
|
|
|
| 32 |
},
|
| 33 |
{
|
| 34 |
+
"id": 3,
|
| 35 |
"content": "MASK",
|
| 36 |
"single_word": false,
|
| 37 |
"lstrip": false,
|
| 38 |
"rstrip": false,
|
| 39 |
"normalized": false,
|
| 40 |
+
"special": true
|
|
|
|
| 41 |
},
|
| 42 |
{
|
| 43 |
+
"id": 4,
|
| 44 |
"content": "BOS",
|
| 45 |
"single_word": false,
|
| 46 |
"lstrip": false,
|
| 47 |
"rstrip": false,
|
| 48 |
"normalized": false,
|
| 49 |
+
"special": true
|
|
|
|
| 50 |
},
|
| 51 |
{
|
| 52 |
+
"id": 5,
|
| 53 |
"content": "EOS",
|
| 54 |
"single_word": false,
|
| 55 |
"lstrip": false,
|
| 56 |
"rstrip": false,
|
| 57 |
"normalized": false,
|
| 58 |
+
"special": true
|
|
|
|
| 59 |
}
|
| 60 |
],
|
| 61 |
"normalizer": null,
|
tokenizer_config.json
CHANGED
|
@@ -6,8 +6,7 @@
|
|
| 6 |
"lstrip": false,
|
| 7 |
"rstrip": false,
|
| 8 |
"normalized": false,
|
| 9 |
-
"special": true
|
| 10 |
-
"id": 0
|
| 11 |
},
|
| 12 |
"1": {
|
| 13 |
"content": "UNK__",
|
|
@@ -15,8 +14,7 @@
|
|
| 15 |
"lstrip": false,
|
| 16 |
"rstrip": false,
|
| 17 |
"normalized": false,
|
| 18 |
-
"special": true
|
| 19 |
-
"id": 1
|
| 20 |
},
|
| 21 |
"2": {
|
| 22 |
"content": "UNK",
|
|
@@ -24,8 +22,7 @@
|
|
| 24 |
"lstrip": false,
|
| 25 |
"rstrip": false,
|
| 26 |
"normalized": false,
|
| 27 |
-
"special": true
|
| 28 |
-
"id": 2
|
| 29 |
},
|
| 30 |
"3": {
|
| 31 |
"content": "MASK",
|
|
@@ -33,8 +30,7 @@
|
|
| 33 |
"lstrip": false,
|
| 34 |
"rstrip": false,
|
| 35 |
"normalized": false,
|
| 36 |
-
"special": true
|
| 37 |
-
"id": 3
|
| 38 |
},
|
| 39 |
"4": {
|
| 40 |
"content": "BOS",
|
|
@@ -42,8 +38,7 @@
|
|
| 42 |
"lstrip": false,
|
| 43 |
"rstrip": false,
|
| 44 |
"normalized": false,
|
| 45 |
-
"special": true
|
| 46 |
-
"id": 4
|
| 47 |
},
|
| 48 |
"5": {
|
| 49 |
"content": "EOS",
|
|
@@ -51,8 +46,7 @@
|
|
| 51 |
"lstrip": false,
|
| 52 |
"rstrip": false,
|
| 53 |
"normalized": false,
|
| 54 |
-
"special": true
|
| 55 |
-
"id": 5
|
| 56 |
}
|
| 57 |
},
|
| 58 |
"clean_up_tokenization_spaces": false,
|
|
|
|
| 6 |
"lstrip": false,
|
| 7 |
"rstrip": false,
|
| 8 |
"normalized": false,
|
| 9 |
+
"special": true
|
|
|
|
| 10 |
},
|
| 11 |
"1": {
|
| 12 |
"content": "UNK__",
|
|
|
|
| 14 |
"lstrip": false,
|
| 15 |
"rstrip": false,
|
| 16 |
"normalized": false,
|
| 17 |
+
"special": true
|
|
|
|
| 18 |
},
|
| 19 |
"2": {
|
| 20 |
"content": "UNK",
|
|
|
|
| 22 |
"lstrip": false,
|
| 23 |
"rstrip": false,
|
| 24 |
"normalized": false,
|
| 25 |
+
"special": true
|
|
|
|
| 26 |
},
|
| 27 |
"3": {
|
| 28 |
"content": "MASK",
|
|
|
|
| 30 |
"lstrip": false,
|
| 31 |
"rstrip": false,
|
| 32 |
"normalized": false,
|
| 33 |
+
"special": true
|
|
|
|
| 34 |
},
|
| 35 |
"4": {
|
| 36 |
"content": "BOS",
|
|
|
|
| 38 |
"lstrip": false,
|
| 39 |
"rstrip": false,
|
| 40 |
"normalized": false,
|
| 41 |
+
"special": true
|
|
|
|
| 42 |
},
|
| 43 |
"5": {
|
| 44 |
"content": "EOS",
|
|
|
|
| 46 |
"lstrip": false,
|
| 47 |
"rstrip": false,
|
| 48 |
"normalized": false,
|
| 49 |
+
"special": true
|
|
|
|
| 50 |
}
|
| 51 |
},
|
| 52 |
"clean_up_tokenization_spaces": false,
|