Commit
•
a0a2fbe
1
Parent(s):
bccf186
Upload tokenizer
Browse files- special_tokens_map.json +5 -21
- tokenizer.json +0 -0
- tokenizer_config.json +12 -30
- vocab.txt +0 -0
special_tokens_map.json
CHANGED
|
@@ -1,23 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
-
"eos_token": {
|
| 10 |
-
"content": "<|endoftext|>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": true,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
-
"unk_token": {
|
| 17 |
-
"content": "<|endoftext|>",
|
| 18 |
-
"lstrip": false,
|
| 19 |
-
"normalized": true,
|
| 20 |
-
"rstrip": false,
|
| 21 |
-
"single_word": false
|
| 22 |
-
}
|
| 23 |
}
|
|
|
|
| 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
CHANGED
|
@@ -1,33 +1,15 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token": false,
|
| 3 |
-
"add_prefix_space": false,
|
| 4 |
-
"bos_token": {
|
| 5 |
-
"__type": "AddedToken",
|
| 6 |
-
"content": "<|endoftext|>",
|
| 7 |
-
"lstrip": false,
|
| 8 |
-
"normalized": true,
|
| 9 |
-
"rstrip": false,
|
| 10 |
-
"single_word": false
|
| 11 |
-
},
|
| 12 |
"clean_up_tokenization_spaces": true,
|
| 13 |
-
"
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
"
|
| 22 |
-
"
|
| 23 |
-
"
|
| 24 |
-
"
|
| 25 |
-
"unk_token": {
|
| 26 |
-
"__type": "AddedToken",
|
| 27 |
-
"content": "<|endoftext|>",
|
| 28 |
-
"lstrip": false,
|
| 29 |
-
"normalized": true,
|
| 30 |
-
"rstrip": false,
|
| 31 |
-
"single_word": false
|
| 32 |
-
}
|
| 33 |
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_basic_tokenize": true,
|
| 5 |
+
"do_lower_case": true,
|
| 6 |
+
"mask_token": "[MASK]",
|
| 7 |
+
"model_max_length": 512,
|
| 8 |
+
"never_split": null,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"strip_accents": null,
|
| 12 |
+
"tokenize_chinese_chars": true,
|
| 13 |
+
"tokenizer_class": "BertTokenizer",
|
| 14 |
+
"unk_token": "[UNK]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|