Upload tokenizer
Browse files- README.md +2 -2
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- vocab.txt +0 -0
README.md
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
datasets:
|
| 4 |
- wikimedia/wikipedia
|
| 5 |
- bookcorpus
|
| 6 |
- nomic-ai/nomic-bert-2048-pretraining-data
|
| 7 |
-
language:
|
| 8 |
-
- en
|
| 9 |
inference: false
|
| 10 |
---
|
| 11 |
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
license: apache-2.0
|
| 5 |
datasets:
|
| 6 |
- wikimedia/wikipedia
|
| 7 |
- bookcorpus
|
| 8 |
- nomic-ai/nomic-bert-2048-pretraining-data
|
|
|
|
|
|
|
| 9 |
inference: false
|
| 10 |
---
|
| 11 |
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 512,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "BertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|