Upload tokenizer
Browse files- added_tokens.json +3 -0
- tokenizer.json +10 -6
- tokenizer_config.json +1 -1
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[LF]": 28996
|
| 3 |
+
}
|
tokenizer.json
CHANGED
|
@@ -1,11 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
"direction": "Right",
|
| 5 |
-
"max_length": 512,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
|
@@ -52,6 +47,15 @@
|
|
| 52 |
"rstrip": false,
|
| 53 |
"normalized": false,
|
| 54 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
}
|
| 56 |
],
|
| 57 |
"normalizer": {
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
|
|
|
| 47 |
"rstrip": false,
|
| 48 |
"normalized": false,
|
| 49 |
"special": true
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"id": 28996,
|
| 53 |
+
"content": "[LF]",
|
| 54 |
+
"single_word": false,
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"special": false
|
| 59 |
}
|
| 60 |
],
|
| 61 |
"normalizer": {
|
tokenizer_config.json
CHANGED
|
@@ -3,7 +3,7 @@
|
|
| 3 |
"do_lower_case": false,
|
| 4 |
"mask_token": "[MASK]",
|
| 5 |
"model_max_length": 512,
|
| 6 |
-
"name_or_path": "
|
| 7 |
"pad_token": "[PAD]",
|
| 8 |
"sep_token": "[SEP]",
|
| 9 |
"special_tokens_map_file": null,
|
|
|
|
| 3 |
"do_lower_case": false,
|
| 4 |
"mask_token": "[MASK]",
|
| 5 |
"model_max_length": 512,
|
| 6 |
+
"name_or_path": "Dizex/FoodBaseBERT",
|
| 7 |
"pad_token": "[PAD]",
|
| 8 |
"sep_token": "[SEP]",
|
| 9 |
"special_tokens_map_file": null,
|