Upload tokenizer
Browse files- added_tokens.json +3 -0
- special_tokens_map.json +63 -0
- tokenizer_config.json +79 -0
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<mask_doc>": 250054
|
3 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"af_ZA",
|
29 |
+
"az_AZ",
|
30 |
+
"bn_IN",
|
31 |
+
"fa_IR",
|
32 |
+
"he_IL",
|
33 |
+
"hr_HR",
|
34 |
+
"id_ID",
|
35 |
+
"ka_GE",
|
36 |
+
"km_KH",
|
37 |
+
"mk_MK",
|
38 |
+
"ml_IN",
|
39 |
+
"mn_MN",
|
40 |
+
"mr_IN",
|
41 |
+
"pl_PL",
|
42 |
+
"ps_AF",
|
43 |
+
"pt_XX",
|
44 |
+
"sv_SE",
|
45 |
+
"sw_KE",
|
46 |
+
"ta_IN",
|
47 |
+
"te_IN",
|
48 |
+
"th_TH",
|
49 |
+
"tl_XX",
|
50 |
+
"uk_UA",
|
51 |
+
"ur_PK",
|
52 |
+
"xh_ZA",
|
53 |
+
"gl_ES",
|
54 |
+
"sl_SI"
|
55 |
+
],
|
56 |
+
"bos_token": "<s>",
|
57 |
+
"cls_token": "<s>",
|
58 |
+
"eos_token": "</s>",
|
59 |
+
"mask_token": "<mask>",
|
60 |
+
"pad_token": "<pad>",
|
61 |
+
"sep_token": "</s>",
|
62 |
+
"unk_token": "<unk>"
|
63 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"af_ZA",
|
29 |
+
"az_AZ",
|
30 |
+
"bn_IN",
|
31 |
+
"fa_IR",
|
32 |
+
"he_IL",
|
33 |
+
"hr_HR",
|
34 |
+
"id_ID",
|
35 |
+
"ka_GE",
|
36 |
+
"km_KH",
|
37 |
+
"mk_MK",
|
38 |
+
"ml_IN",
|
39 |
+
"mn_MN",
|
40 |
+
"mr_IN",
|
41 |
+
"pl_PL",
|
42 |
+
"ps_AF",
|
43 |
+
"pt_XX",
|
44 |
+
"sv_SE",
|
45 |
+
"sw_KE",
|
46 |
+
"ta_IN",
|
47 |
+
"te_IN",
|
48 |
+
"th_TH",
|
49 |
+
"tl_XX",
|
50 |
+
"uk_UA",
|
51 |
+
"ur_PK",
|
52 |
+
"xh_ZA",
|
53 |
+
"gl_ES",
|
54 |
+
"sl_SI"
|
55 |
+
],
|
56 |
+
"bos_token": "<s>",
|
57 |
+
"cls_token": "<s>",
|
58 |
+
"eos_token": "</s>",
|
59 |
+
"language_codes": "ML50",
|
60 |
+
"mask_token": {
|
61 |
+
"__type": "AddedToken",
|
62 |
+
"content": "<mask>",
|
63 |
+
"lstrip": true,
|
64 |
+
"normalized": true,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false
|
67 |
+
},
|
68 |
+
"model_max_length": 1000000000000000019884624838656,
|
69 |
+
"name_or_path": "PISCES",
|
70 |
+
"pad_token": "<pad>",
|
71 |
+
"sep_token": "</s>",
|
72 |
+
"sp_model_kwargs": {},
|
73 |
+
"special_tokens_map_file": "/home/suraj/projects/mbart-50/mbart-50/special_tokens_map.json",
|
74 |
+
"src_lang": null,
|
75 |
+
"tgt_lang": null,
|
76 |
+
"tokenizer_class": "MBart50Tokenizer",
|
77 |
+
"tokenizer_file": null,
|
78 |
+
"unk_token": "<unk>"
|
79 |
+
}
|