add tokenizer
Browse files- sentencepiece.bpe.model +2 -2
- special_tokens_map.json +100 -210
- tokenizer_config.json +108 -13
- vocab.json +0 -0
sentencepiece.bpe.model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8f7c76ed2a5e0822be39f0a4f95a55eb19c78f4593ce609e2edbc2aea4d380a
|
3 |
+
size 2423393
|
special_tokens_map.json
CHANGED
@@ -1,218 +1,108 @@
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
12 |
-
"
|
13 |
-
"
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"
|
30 |
-
"
|
31 |
-
"
|
32 |
-
"
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"
|
36 |
-
"
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"
|
40 |
-
"
|
41 |
-
"
|
42 |
-
"
|
43 |
-
"
|
44 |
-
"
|
45 |
-
"
|
46 |
-
"
|
47 |
-
"
|
48 |
-
"
|
49 |
-
"
|
50 |
-
"
|
51 |
-
"
|
52 |
-
"
|
53 |
-
"
|
54 |
-
"
|
55 |
-
"
|
56 |
-
"
|
57 |
-
"
|
58 |
-
"
|
59 |
-
"
|
60 |
-
"
|
61 |
-
"
|
62 |
-
"
|
63 |
-
"
|
64 |
-
"
|
65 |
-
"
|
66 |
-
"
|
67 |
-
"
|
68 |
-
"
|
69 |
-
"
|
70 |
-
"
|
71 |
-
"
|
72 |
-
"
|
73 |
-
"
|
74 |
-
"
|
75 |
-
"
|
76 |
-
"
|
77 |
-
"
|
78 |
-
"
|
79 |
-
"
|
80 |
-
"
|
81 |
-
"
|
82 |
-
"
|
83 |
-
"
|
84 |
-
"
|
85 |
-
"
|
86 |
-
"
|
87 |
-
"
|
88 |
-
"
|
89 |
-
"
|
90 |
-
"
|
91 |
-
"
|
92 |
-
"
|
93 |
-
"
|
94 |
-
"
|
95 |
-
"
|
96 |
-
"
|
97 |
-
"
|
98 |
-
"
|
99 |
-
"
|
100 |
-
"
|
101 |
-
"
|
102 |
-
"
|
103 |
-
"lvs_Latn",
|
104 |
-
"lij_Latn",
|
105 |
-
"lim_Latn",
|
106 |
-
"lin_Latn",
|
107 |
-
"lit_Latn",
|
108 |
-
"lmo_Latn",
|
109 |
-
"ltg_Latn",
|
110 |
-
"ltz_Latn",
|
111 |
-
"lua_Latn",
|
112 |
-
"lug_Latn",
|
113 |
-
"luo_Latn",
|
114 |
-
"lus_Latn",
|
115 |
-
"mag_Deva",
|
116 |
-
"mai_Deva",
|
117 |
-
"mal_Mlym",
|
118 |
-
"mar_Deva",
|
119 |
-
"min_Latn",
|
120 |
-
"mkd_Cyrl",
|
121 |
-
"plt_Latn",
|
122 |
-
"mlt_Latn",
|
123 |
-
"mni_Beng",
|
124 |
-
"khk_Cyrl",
|
125 |
-
"mos_Latn",
|
126 |
-
"mri_Latn",
|
127 |
-
"zsm_Latn",
|
128 |
-
"mya_Mymr",
|
129 |
-
"nld_Latn",
|
130 |
-
"nno_Latn",
|
131 |
-
"nob_Latn",
|
132 |
-
"npi_Deva",
|
133 |
-
"nso_Latn",
|
134 |
-
"nus_Latn",
|
135 |
-
"nya_Latn",
|
136 |
-
"oci_Latn",
|
137 |
-
"gaz_Latn",
|
138 |
-
"ory_Orya",
|
139 |
-
"pag_Latn",
|
140 |
-
"pan_Guru",
|
141 |
-
"pap_Latn",
|
142 |
-
"pol_Latn",
|
143 |
-
"por_Latn",
|
144 |
-
"prs_Arab",
|
145 |
-
"pbt_Arab",
|
146 |
-
"quy_Latn",
|
147 |
-
"ron_Latn",
|
148 |
-
"run_Latn",
|
149 |
-
"rus_Cyrl",
|
150 |
-
"sag_Latn",
|
151 |
-
"san_Deva",
|
152 |
-
"sat_Beng",
|
153 |
-
"scn_Latn",
|
154 |
-
"shn_Mymr",
|
155 |
-
"sin_Sinh",
|
156 |
-
"slk_Latn",
|
157 |
-
"slv_Latn",
|
158 |
-
"smo_Latn",
|
159 |
-
"sna_Latn",
|
160 |
-
"snd_Arab",
|
161 |
-
"som_Latn",
|
162 |
-
"sot_Latn",
|
163 |
-
"spa_Latn",
|
164 |
-
"als_Latn",
|
165 |
-
"srd_Latn",
|
166 |
-
"srp_Cyrl",
|
167 |
-
"ssw_Latn",
|
168 |
-
"sun_Latn",
|
169 |
-
"swe_Latn",
|
170 |
-
"swh_Latn",
|
171 |
-
"szl_Latn",
|
172 |
-
"tam_Taml",
|
173 |
-
"tat_Cyrl",
|
174 |
-
"tel_Telu",
|
175 |
-
"tgk_Cyrl",
|
176 |
-
"tgl_Latn",
|
177 |
-
"tha_Thai",
|
178 |
-
"tir_Ethi",
|
179 |
-
"taq_Latn",
|
180 |
-
"taq_Tfng",
|
181 |
-
"tpi_Latn",
|
182 |
-
"tsn_Latn",
|
183 |
-
"tso_Latn",
|
184 |
-
"tuk_Latn",
|
185 |
-
"tum_Latn",
|
186 |
-
"tur_Latn",
|
187 |
-
"twi_Latn",
|
188 |
-
"tzm_Tfng",
|
189 |
-
"uig_Arab",
|
190 |
-
"ukr_Cyrl",
|
191 |
-
"umb_Latn",
|
192 |
-
"urd_Arab",
|
193 |
-
"uzn_Latn",
|
194 |
-
"vec_Latn",
|
195 |
-
"vie_Latn",
|
196 |
-
"war_Latn",
|
197 |
-
"wol_Latn",
|
198 |
-
"xho_Latn",
|
199 |
-
"ydd_Hebr",
|
200 |
-
"yor_Latn",
|
201 |
-
"yue_Hant",
|
202 |
-
"zho_Hans",
|
203 |
-
"zho_Hant",
|
204 |
-
"zul_Latn"
|
205 |
],
|
206 |
"bos_token": "<s>",
|
207 |
-
"cls_token": "<s>",
|
208 |
"eos_token": "</s>",
|
209 |
-
"mask_token": {
|
210 |
-
"content": "<mask>",
|
211 |
-
"lstrip": true,
|
212 |
-
"normalized": true,
|
213 |
-
"rstrip": false,
|
214 |
-
"single_word": false
|
215 |
-
},
|
216 |
"pad_token": "<pad>",
|
217 |
"sep_token": "</s>",
|
218 |
"unk_token": "<unk>"
|
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
+
"__af__",
|
4 |
+
"__am__",
|
5 |
+
"__ar__",
|
6 |
+
"__ast__",
|
7 |
+
"__az__",
|
8 |
+
"__ba__",
|
9 |
+
"__be__",
|
10 |
+
"__bg__",
|
11 |
+
"__bn__",
|
12 |
+
"__br__",
|
13 |
+
"__bs__",
|
14 |
+
"__ca__",
|
15 |
+
"__ceb__",
|
16 |
+
"__cs__",
|
17 |
+
"__cy__",
|
18 |
+
"__da__",
|
19 |
+
"__de__",
|
20 |
+
"__el__",
|
21 |
+
"__en__",
|
22 |
+
"__es__",
|
23 |
+
"__et__",
|
24 |
+
"__fa__",
|
25 |
+
"__ff__",
|
26 |
+
"__fi__",
|
27 |
+
"__fr__",
|
28 |
+
"__fy__",
|
29 |
+
"__ga__",
|
30 |
+
"__gd__",
|
31 |
+
"__gl__",
|
32 |
+
"__gu__",
|
33 |
+
"__ha__",
|
34 |
+
"__he__",
|
35 |
+
"__hi__",
|
36 |
+
"__hr__",
|
37 |
+
"__ht__",
|
38 |
+
"__hu__",
|
39 |
+
"__hy__",
|
40 |
+
"__id__",
|
41 |
+
"__ig__",
|
42 |
+
"__ilo__",
|
43 |
+
"__is__",
|
44 |
+
"__it__",
|
45 |
+
"__ja__",
|
46 |
+
"__jv__",
|
47 |
+
"__ka__",
|
48 |
+
"__kk__",
|
49 |
+
"__km__",
|
50 |
+
"__kn__",
|
51 |
+
"__ko__",
|
52 |
+
"__lb__",
|
53 |
+
"__lg__",
|
54 |
+
"__ln__",
|
55 |
+
"__lo__",
|
56 |
+
"__lt__",
|
57 |
+
"__lv__",
|
58 |
+
"__mg__",
|
59 |
+
"__mk__",
|
60 |
+
"__ml__",
|
61 |
+
"__mn__",
|
62 |
+
"__mr__",
|
63 |
+
"__ms__",
|
64 |
+
"__my__",
|
65 |
+
"__ne__",
|
66 |
+
"__nl__",
|
67 |
+
"__no__",
|
68 |
+
"__ns__",
|
69 |
+
"__oc__",
|
70 |
+
"__or__",
|
71 |
+
"__pa__",
|
72 |
+
"__pl__",
|
73 |
+
"__ps__",
|
74 |
+
"__pt__",
|
75 |
+
"__ro__",
|
76 |
+
"__ru__",
|
77 |
+
"__sd__",
|
78 |
+
"__si__",
|
79 |
+
"__sk__",
|
80 |
+
"__sl__",
|
81 |
+
"__so__",
|
82 |
+
"__sq__",
|
83 |
+
"__sr__",
|
84 |
+
"__ss__",
|
85 |
+
"__su__",
|
86 |
+
"__sv__",
|
87 |
+
"__sw__",
|
88 |
+
"__ta__",
|
89 |
+
"__th__",
|
90 |
+
"__tl__",
|
91 |
+
"__tn__",
|
92 |
+
"__tr__",
|
93 |
+
"__uk__",
|
94 |
+
"__ur__",
|
95 |
+
"__uz__",
|
96 |
+
"__vi__",
|
97 |
+
"__wo__",
|
98 |
+
"__xh__",
|
99 |
+
"__yi__",
|
100 |
+
"__yo__",
|
101 |
+
"__zh__",
|
102 |
+
"__zu__"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
103 |
],
|
104 |
"bos_token": "<s>",
|
|
|
105 |
"eos_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
106 |
"pad_token": "<pad>",
|
107 |
"sep_token": "</s>",
|
108 |
"unk_token": "<unk>"
|
tokenizer_config.json
CHANGED
@@ -1,24 +1,119 @@
|
|
1 |
{
|
2 |
-
"additional_special_tokens":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"bos_token": "<s>",
|
4 |
-
"cls_token": "<s>",
|
5 |
"eos_token": "</s>",
|
6 |
-
"
|
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/
|
|
|
16 |
"pad_token": "<pad>",
|
17 |
"sep_token": "</s>",
|
18 |
"sp_model_kwargs": {},
|
19 |
-
"special_tokens_map_file":
|
20 |
"src_lang": "ru",
|
21 |
"tgt_lang": "zu",
|
22 |
-
"tokenizer_class": "
|
|
|
23 |
"unk_token": "<unk>"
|
24 |
}
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"__af__",
|
4 |
+
"__am__",
|
5 |
+
"__ar__",
|
6 |
+
"__ast__",
|
7 |
+
"__az__",
|
8 |
+
"__ba__",
|
9 |
+
"__be__",
|
10 |
+
"__bg__",
|
11 |
+
"__bn__",
|
12 |
+
"__br__",
|
13 |
+
"__bs__",
|
14 |
+
"__ca__",
|
15 |
+
"__ceb__",
|
16 |
+
"__cs__",
|
17 |
+
"__cy__",
|
18 |
+
"__da__",
|
19 |
+
"__de__",
|
20 |
+
"__el__",
|
21 |
+
"__en__",
|
22 |
+
"__es__",
|
23 |
+
"__et__",
|
24 |
+
"__fa__",
|
25 |
+
"__ff__",
|
26 |
+
"__fi__",
|
27 |
+
"__fr__",
|
28 |
+
"__fy__",
|
29 |
+
"__ga__",
|
30 |
+
"__gd__",
|
31 |
+
"__gl__",
|
32 |
+
"__gu__",
|
33 |
+
"__ha__",
|
34 |
+
"__he__",
|
35 |
+
"__hi__",
|
36 |
+
"__hr__",
|
37 |
+
"__ht__",
|
38 |
+
"__hu__",
|
39 |
+
"__hy__",
|
40 |
+
"__id__",
|
41 |
+
"__ig__",
|
42 |
+
"__ilo__",
|
43 |
+
"__is__",
|
44 |
+
"__it__",
|
45 |
+
"__ja__",
|
46 |
+
"__jv__",
|
47 |
+
"__ka__",
|
48 |
+
"__kk__",
|
49 |
+
"__km__",
|
50 |
+
"__kn__",
|
51 |
+
"__ko__",
|
52 |
+
"__lb__",
|
53 |
+
"__lg__",
|
54 |
+
"__ln__",
|
55 |
+
"__lo__",
|
56 |
+
"__lt__",
|
57 |
+
"__lv__",
|
58 |
+
"__mg__",
|
59 |
+
"__mk__",
|
60 |
+
"__ml__",
|
61 |
+
"__mn__",
|
62 |
+
"__mr__",
|
63 |
+
"__ms__",
|
64 |
+
"__my__",
|
65 |
+
"__ne__",
|
66 |
+
"__nl__",
|
67 |
+
"__no__",
|
68 |
+
"__ns__",
|
69 |
+
"__oc__",
|
70 |
+
"__or__",
|
71 |
+
"__pa__",
|
72 |
+
"__pl__",
|
73 |
+
"__ps__",
|
74 |
+
"__pt__",
|
75 |
+
"__ro__",
|
76 |
+
"__ru__",
|
77 |
+
"__sd__",
|
78 |
+
"__si__",
|
79 |
+
"__sk__",
|
80 |
+
"__sl__",
|
81 |
+
"__so__",
|
82 |
+
"__sq__",
|
83 |
+
"__sr__",
|
84 |
+
"__ss__",
|
85 |
+
"__su__",
|
86 |
+
"__sv__",
|
87 |
+
"__sw__",
|
88 |
+
"__ta__",
|
89 |
+
"__th__",
|
90 |
+
"__tl__",
|
91 |
+
"__tn__",
|
92 |
+
"__tr__",
|
93 |
+
"__uk__",
|
94 |
+
"__ur__",
|
95 |
+
"__uz__",
|
96 |
+
"__vi__",
|
97 |
+
"__wo__",
|
98 |
+
"__xh__",
|
99 |
+
"__yi__",
|
100 |
+
"__yo__",
|
101 |
+
"__zh__",
|
102 |
+
"__zu__"
|
103 |
+
],
|
104 |
"bos_token": "<s>",
|
|
|
105 |
"eos_token": "</s>",
|
106 |
+
"language_codes": "m2m100",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
107 |
"model_max_length": 1024,
|
108 |
+
"name_or_path": "facebook/m2m100_418M",
|
109 |
+
"num_madeup_words": 8,
|
110 |
"pad_token": "<pad>",
|
111 |
"sep_token": "</s>",
|
112 |
"sp_model_kwargs": {},
|
113 |
+
"special_tokens_map_file": "m2m_100_1.2B_v2/special_tokens_map.json",
|
114 |
"src_lang": "ru",
|
115 |
"tgt_lang": "zu",
|
116 |
+
"tokenizer_class": "M2M100Tokenizer",
|
117 |
+
"tokenizer_file": null,
|
118 |
"unk_token": "<unk>"
|
119 |
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|