Upload folder using huggingface_hub
Browse files- tokenizer.json +13 -14
- tokenizer_config.json +0 -0
tokenizer.json
CHANGED
|
@@ -1,14 +1,13 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
|
|
|
| 4 |
"max_length": 128,
|
| 5 |
"strategy": "LongestFirst",
|
| 6 |
"stride": 0
|
| 7 |
},
|
| 8 |
"padding": {
|
| 9 |
-
"strategy":
|
| 10 |
-
"Fixed": 128
|
| 11 |
-
},
|
| 12 |
"direction": "Right",
|
| 13 |
"pad_to_multiple_of": null,
|
| 14 |
"pad_id": 0,
|
|
@@ -18,48 +17,48 @@
|
|
| 18 |
"added_tokens": [
|
| 19 |
{
|
| 20 |
"id": 0,
|
| 21 |
-
"special": true,
|
| 22 |
"content": "[PAD]",
|
| 23 |
"single_word": false,
|
| 24 |
"lstrip": false,
|
| 25 |
"rstrip": false,
|
| 26 |
-
"normalized": false
|
|
|
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"id": 100,
|
| 30 |
-
"special": true,
|
| 31 |
"content": "[UNK]",
|
| 32 |
"single_word": false,
|
| 33 |
"lstrip": false,
|
| 34 |
"rstrip": false,
|
| 35 |
-
"normalized": false
|
|
|
|
| 36 |
},
|
| 37 |
{
|
| 38 |
"id": 101,
|
| 39 |
-
"special": true,
|
| 40 |
"content": "[CLS]",
|
| 41 |
"single_word": false,
|
| 42 |
"lstrip": false,
|
| 43 |
"rstrip": false,
|
| 44 |
-
"normalized": false
|
|
|
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"id": 102,
|
| 48 |
-
"special": true,
|
| 49 |
"content": "[SEP]",
|
| 50 |
"single_word": false,
|
| 51 |
"lstrip": false,
|
| 52 |
"rstrip": false,
|
| 53 |
-
"normalized": false
|
|
|
|
| 54 |
},
|
| 55 |
{
|
| 56 |
"id": 103,
|
| 57 |
-
"special": true,
|
| 58 |
"content": "[MASK]",
|
| 59 |
"single_word": false,
|
| 60 |
"lstrip": false,
|
| 61 |
"rstrip": false,
|
| 62 |
-
"normalized": false
|
|
|
|
| 63 |
}
|
| 64 |
],
|
| 65 |
"normalizer": {
|
|
@@ -30682,4 +30681,4 @@
|
|
| 30682 |
"##～": 30521
|
| 30683 |
}
|
| 30684 |
}
|
| 30685 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
"max_length": 128,
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
"padding": {
|
| 10 |
+
"strategy": "BatchLongest",
|
|
|
|
|
|
|
| 11 |
"direction": "Right",
|
| 12 |
"pad_to_multiple_of": null,
|
| 13 |
"pad_id": 0,
|
|
|
|
| 17 |
"added_tokens": [
|
| 18 |
{
|
| 19 |
"id": 0,
|
|
|
|
| 20 |
"content": "[PAD]",
|
| 21 |
"single_word": false,
|
| 22 |
"lstrip": false,
|
| 23 |
"rstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"special": true
|
| 26 |
},
|
| 27 |
{
|
| 28 |
"id": 100,
|
|
|
|
| 29 |
"content": "[UNK]",
|
| 30 |
"single_word": false,
|
| 31 |
"lstrip": false,
|
| 32 |
"rstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"special": true
|
| 35 |
},
|
| 36 |
{
|
| 37 |
"id": 101,
|
|
|
|
| 38 |
"content": "[CLS]",
|
| 39 |
"single_word": false,
|
| 40 |
"lstrip": false,
|
| 41 |
"rstrip": false,
|
| 42 |
+
"normalized": false,
|
| 43 |
+
"special": true
|
| 44 |
},
|
| 45 |
{
|
| 46 |
"id": 102,
|
|
|
|
| 47 |
"content": "[SEP]",
|
| 48 |
"single_word": false,
|
| 49 |
"lstrip": false,
|
| 50 |
"rstrip": false,
|
| 51 |
+
"normalized": false,
|
| 52 |
+
"special": true
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"id": 103,
|
|
|
|
| 56 |
"content": "[MASK]",
|
| 57 |
"single_word": false,
|
| 58 |
"lstrip": false,
|
| 59 |
"rstrip": false,
|
| 60 |
+
"normalized": false,
|
| 61 |
+
"special": true
|
| 62 |
}
|
| 63 |
],
|
| 64 |
"normalizer": {
|
|
|
|
| 30681 |
"##～": 30521
|
| 30682 |
}
|
| 30683 |
}
|
| 30684 |
+
}
|
tokenizer_config.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|