Upload tokenizer
Browse files- added_tokens.json +26 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +18 -0
- tokenizer.json +0 -0
- tokenizer_config.json +23 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<hl>": 85729,
|
| 3 |
+
"ar_AR": 85706,
|
| 4 |
+
"cs_CZ": 85707,
|
| 5 |
+
"es_XX": 85708,
|
| 6 |
+
"et_EE": 85709,
|
| 7 |
+
"fi_FI": 85710,
|
| 8 |
+
"fr_XX": 85711,
|
| 9 |
+
"gu_IN": 85712,
|
| 10 |
+
"hi_IN": 85713,
|
| 11 |
+
"it_IT": 85714,
|
| 12 |
+
"ja_XX": 85715,
|
| 13 |
+
"kk_KZ": 85716,
|
| 14 |
+
"ko_KR": 85717,
|
| 15 |
+
"lt_LT": 85718,
|
| 16 |
+
"lv_LV": 85719,
|
| 17 |
+
"my_MM": 85720,
|
| 18 |
+
"ne_NP": 85721,
|
| 19 |
+
"nl_XX": 85722,
|
| 20 |
+
"ro_RO": 85723,
|
| 21 |
+
"ru_RU": 85724,
|
| 22 |
+
"si_LK": 85725,
|
| 23 |
+
"tr_TR": 85726,
|
| 24 |
+
"vi_VN": 85727,
|
| 25 |
+
"zh_CN": 85728
|
| 26 |
+
}
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<hl>"
|
| 4 |
+
],
|
| 5 |
+
"bos_token": "<s>",
|
| 6 |
+
"cls_token": "<s>",
|
| 7 |
+
"eos_token": "</s>",
|
| 8 |
+
"mask_token": {
|
| 9 |
+
"content": "<mask>",
|
| 10 |
+
"lstrip": true,
|
| 11 |
+
"normalized": false,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
},
|
| 15 |
+
"pad_token": "<pad>",
|
| 16 |
+
"sep_token": "</s>",
|
| 17 |
+
"unk_token": "<unk>"
|
| 18 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": null,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"mask_token": {
|
| 7 |
+
"__type": "AddedToken",
|
| 8 |
+
"content": "<mask>",
|
| 9 |
+
"lstrip": true,
|
| 10 |
+
"normalized": true,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"single_word": false
|
| 13 |
+
},
|
| 14 |
+
"model_max_length": 1024,
|
| 15 |
+
"name_or_path": "ckpts/mbart-large-cc25-frquad-qg-trimmed-fr",
|
| 16 |
+
"pad_token": "<pad>",
|
| 17 |
+
"sep_token": "</s>",
|
| 18 |
+
"special_tokens_map_file": null,
|
| 19 |
+
"src_lang": null,
|
| 20 |
+
"tgt_lang": null,
|
| 21 |
+
"tokenizer_class": "MBartTokenizer",
|
| 22 |
+
"unk_token": "<unk>"
|
| 23 |
+
}
|