Commit
•
6726507
1
Parent(s):
1f99117
Upload tokenizer
Browse files- README.md +5 -5
- special_tokens_map.json +35 -0
- tokenizer.json +0 -0
- tokenizer_config.json +19 -14
README.md
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
---
|
| 2 |
-
license: mit
|
| 3 |
-
pipeline_tag: fill-mask
|
| 4 |
-
datasets:
|
| 5 |
-
- arch-be/brabant-xvii
|
| 6 |
language:
|
| 7 |
- nl
|
| 8 |
- fr
|
| 9 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
language:
|
| 3 |
- nl
|
| 4 |
- fr
|
| 5 |
+
license: mit
|
| 6 |
+
datasets:
|
| 7 |
+
- arch-be/brabant-xvii
|
| 8 |
+
pipeline_tag: fill-mask
|
| 9 |
+
---
|
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,25 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"mask_token": {
|
| 3 |
"content": "<mask>",
|
| 4 |
"lstrip": false,
|
|
@@ -12,5 +33,19 @@
|
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
}
|
| 16 |
}
|
|
|
|
| 1 |
{
|
| 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": "<cls>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "<e>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
"mask_token": {
|
| 24 |
"content": "<mask>",
|
| 25 |
"lstrip": false,
|
|
|
|
| 33 |
"normalized": false,
|
| 34 |
"rstrip": false,
|
| 35 |
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "<sep>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "$",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
}
|
| 51 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,54 +1,54 @@
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
-
"
|
| 4 |
-
"content": "
|
| 5 |
"lstrip": false,
|
| 6 |
"normalized": false,
|
| 7 |
"rstrip": false,
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
-
"
|
| 12 |
-
"content": "<
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": false,
|
| 15 |
"rstrip": false,
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
-
"
|
| 20 |
-
"content": "
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
-
"
|
| 28 |
-
"content": "<
|
| 29 |
"lstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
-
"
|
| 36 |
-
"content": "<
|
| 37 |
"lstrip": false,
|
| 38 |
"normalized": false,
|
| 39 |
"rstrip": false,
|
| 40 |
"single_word": false,
|
| 41 |
"special": true
|
| 42 |
},
|
| 43 |
-
"
|
| 44 |
-
"content": "<
|
| 45 |
"lstrip": false,
|
| 46 |
"normalized": false,
|
| 47 |
"rstrip": false,
|
| 48 |
"single_word": false,
|
| 49 |
"special": true
|
| 50 |
},
|
| 51 |
-
"
|
| 52 |
"content": "<mask>",
|
| 53 |
"lstrip": false,
|
| 54 |
"normalized": false,
|
|
@@ -57,9 +57,14 @@
|
|
| 57 |
"special": true
|
| 58 |
}
|
| 59 |
},
|
|
|
|
| 60 |
"clean_up_tokenization_spaces": true,
|
|
|
|
|
|
|
| 61 |
"mask_token": "<mask>",
|
| 62 |
"model_max_length": 1000000000000000019884624838656,
|
| 63 |
"pad_token": "<pad>",
|
| 64 |
-
"
|
|
|
|
|
|
|
| 65 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
+
"129": {
|
| 4 |
+
"content": "$",
|
| 5 |
"lstrip": false,
|
| 6 |
"normalized": false,
|
| 7 |
"rstrip": false,
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
+
"22113": {
|
| 12 |
+
"content": "<s>",
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": false,
|
| 15 |
"rstrip": false,
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
+
"22114": {
|
| 20 |
+
"content": "<e>",
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
+
"22115": {
|
| 28 |
+
"content": "<sep>",
|
| 29 |
"lstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
+
"22116": {
|
| 36 |
+
"content": "<pad>",
|
| 37 |
"lstrip": false,
|
| 38 |
"normalized": false,
|
| 39 |
"rstrip": false,
|
| 40 |
"single_word": false,
|
| 41 |
"special": true
|
| 42 |
},
|
| 43 |
+
"22117": {
|
| 44 |
+
"content": "<cls>",
|
| 45 |
"lstrip": false,
|
| 46 |
"normalized": false,
|
| 47 |
"rstrip": false,
|
| 48 |
"single_word": false,
|
| 49 |
"special": true
|
| 50 |
},
|
| 51 |
+
"22118": {
|
| 52 |
"content": "<mask>",
|
| 53 |
"lstrip": false,
|
| 54 |
"normalized": false,
|
|
|
|
| 57 |
"special": true
|
| 58 |
}
|
| 59 |
},
|
| 60 |
+
"bos_token": "<s>",
|
| 61 |
"clean_up_tokenization_spaces": true,
|
| 62 |
+
"cls_token": "<cls>",
|
| 63 |
+
"eos_token": "<e>",
|
| 64 |
"mask_token": "<mask>",
|
| 65 |
"model_max_length": 1000000000000000019884624838656,
|
| 66 |
"pad_token": "<pad>",
|
| 67 |
+
"sep_token": "<sep>",
|
| 68 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 69 |
+
"unk_token": "$"
|
| 70 |
}
|