Commit
•
0ec1aba
1
Parent(s):
9701cec
Training done
Browse files- added_tokens.json +1 -2
- special_tokens_map.json +7 -49
- tokenizer_config.json +0 -8
added_tokens.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
"<mask>": 64000,
|
| 3 |
-
"<
|
| 4 |
-
"<s_pair_ocr>": 64002
|
| 5 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"<mask>": 64000,
|
| 3 |
+
"<s_pair_ocr>": 64001
|
|
|
|
| 4 |
}
|
special_tokens_map.json
CHANGED
|
@@ -1,51 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 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 |
-
},
|
| 23 |
-
"mask_token": {
|
| 24 |
-
"content": "<mask>",
|
| 25 |
-
"lstrip": false,
|
| 26 |
-
"normalized": false,
|
| 27 |
-
"rstrip": false,
|
| 28 |
-
"single_word": false
|
| 29 |
-
},
|
| 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 |
-
}
|
| 51 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": "<mask>",
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"sep_token": "</s>",
|
| 8 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
}
|
tokenizer_config.json
CHANGED
|
@@ -41,14 +41,6 @@
|
|
| 41 |
"special": true
|
| 42 |
},
|
| 43 |
"64001": {
|
| 44 |
-
"content": "<s_extract-v2>",
|
| 45 |
-
"lstrip": false,
|
| 46 |
-
"normalized": true,
|
| 47 |
-
"rstrip": false,
|
| 48 |
-
"single_word": false,
|
| 49 |
-
"special": false
|
| 50 |
-
},
|
| 51 |
-
"64002": {
|
| 52 |
"content": "<s_pair_ocr>",
|
| 53 |
"lstrip": false,
|
| 54 |
"normalized": true,
|
|
|
|
| 41 |
"special": true
|
| 42 |
},
|
| 43 |
"64001": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
"content": "<s_pair_ocr>",
|
| 45 |
"lstrip": false,
|
| 46 |
"normalized": true,
|