Added tokenizer
Browse files- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +42 -0
- tokenizer_config.json +25 -0
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 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"ar_AR",
|
| 4 |
+
"cs_CZ",
|
| 5 |
+
"de_DE",
|
| 6 |
+
"en_XX",
|
| 7 |
+
"es_XX",
|
| 8 |
+
"et_EE",
|
| 9 |
+
"fi_FI",
|
| 10 |
+
"fr_XX",
|
| 11 |
+
"gu_IN",
|
| 12 |
+
"hi_IN",
|
| 13 |
+
"it_IT",
|
| 14 |
+
"ja_XX",
|
| 15 |
+
"kk_KZ",
|
| 16 |
+
"ko_KR",
|
| 17 |
+
"lt_LT",
|
| 18 |
+
"lv_LV",
|
| 19 |
+
"my_MM",
|
| 20 |
+
"ne_NP",
|
| 21 |
+
"nl_XX",
|
| 22 |
+
"ro_RO",
|
| 23 |
+
"ru_RU",
|
| 24 |
+
"si_LK",
|
| 25 |
+
"tr_TR",
|
| 26 |
+
"vi_VN",
|
| 27 |
+
"zh_CN"
|
| 28 |
+
],
|
| 29 |
+
"bos_token": "<s>",
|
| 30 |
+
"cls_token": "<s>",
|
| 31 |
+
"eos_token": "</s>",
|
| 32 |
+
"mask_token": {
|
| 33 |
+
"content": "<mask>",
|
| 34 |
+
"lstrip": true,
|
| 35 |
+
"normalized": true,
|
| 36 |
+
"rstrip": false,
|
| 37 |
+
"single_word": false
|
| 38 |
+
},
|
| 39 |
+
"pad_token": "<pad>",
|
| 40 |
+
"sep_token": "</s>",
|
| 41 |
+
"unk_token": "<unk>"
|
| 42 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "facebook/mbart-large-cc25",
|
| 16 |
+
"pad_token": "<pad>",
|
| 17 |
+
"sep_token": "</s>",
|
| 18 |
+
"sp_model_kwargs": {},
|
| 19 |
+
"special_tokens_map_file": null,
|
| 20 |
+
"src_lang": null,
|
| 21 |
+
"tgt_lang": null,
|
| 22 |
+
"tokenizer_class": "MBartTokenizer",
|
| 23 |
+
"tokenizer_file": null,
|
| 24 |
+
"unk_token": "<unk>"
|
| 25 |
+
}
|