visheratin
commited on
Commit
•
38f1cde
1
Parent(s):
41725ec
Fix tokenizer.
Browse files- .gitattributes +1 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +213 -18
- tokenizer.json +0 -0
- tokenizer_config.json +17 -26
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14bb8dfb35c0ffdea7bc01e56cea38b9e3d5efcdcb9c251d6b40538e1aab555a
|
3 |
+
size 4852054
|
special_tokens_map.json
CHANGED
@@ -1,24 +1,219 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"normalized": true,
|
6 |
"rstrip": false,
|
7 |
"single_word": false
|
8 |
},
|
9 |
-
"
|
10 |
-
|
11 |
-
|
12 |
-
"normalized": true,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": "<|endoftext|>",
|
17 |
-
"unk_token": {
|
18 |
-
"content": "<|endoftext|>",
|
19 |
-
"lstrip": false,
|
20 |
-
"normalized": true,
|
21 |
-
"rstrip": false,
|
22 |
-
"single_word": false
|
23 |
-
}
|
24 |
}
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"ace_Arab",
|
4 |
+
"ace_Latn",
|
5 |
+
"acm_Arab",
|
6 |
+
"acq_Arab",
|
7 |
+
"aeb_Arab",
|
8 |
+
"afr_Latn",
|
9 |
+
"ajp_Arab",
|
10 |
+
"aka_Latn",
|
11 |
+
"amh_Ethi",
|
12 |
+
"apc_Arab",
|
13 |
+
"arb_Arab",
|
14 |
+
"ars_Arab",
|
15 |
+
"ary_Arab",
|
16 |
+
"arz_Arab",
|
17 |
+
"asm_Beng",
|
18 |
+
"ast_Latn",
|
19 |
+
"awa_Deva",
|
20 |
+
"ayr_Latn",
|
21 |
+
"azb_Arab",
|
22 |
+
"azj_Latn",
|
23 |
+
"bak_Cyrl",
|
24 |
+
"bam_Latn",
|
25 |
+
"ban_Latn",
|
26 |
+
"bel_Cyrl",
|
27 |
+
"bem_Latn",
|
28 |
+
"ben_Beng",
|
29 |
+
"bho_Deva",
|
30 |
+
"bjn_Arab",
|
31 |
+
"bjn_Latn",
|
32 |
+
"bod_Tibt",
|
33 |
+
"bos_Latn",
|
34 |
+
"bug_Latn",
|
35 |
+
"bul_Cyrl",
|
36 |
+
"cat_Latn",
|
37 |
+
"ceb_Latn",
|
38 |
+
"ces_Latn",
|
39 |
+
"cjk_Latn",
|
40 |
+
"ckb_Arab",
|
41 |
+
"crh_Latn",
|
42 |
+
"cym_Latn",
|
43 |
+
"dan_Latn",
|
44 |
+
"deu_Latn",
|
45 |
+
"dik_Latn",
|
46 |
+
"dyu_Latn",
|
47 |
+
"dzo_Tibt",
|
48 |
+
"ell_Grek",
|
49 |
+
"eng_Latn",
|
50 |
+
"epo_Latn",
|
51 |
+
"est_Latn",
|
52 |
+
"eus_Latn",
|
53 |
+
"ewe_Latn",
|
54 |
+
"fao_Latn",
|
55 |
+
"pes_Arab",
|
56 |
+
"fij_Latn",
|
57 |
+
"fin_Latn",
|
58 |
+
"fon_Latn",
|
59 |
+
"fra_Latn",
|
60 |
+
"fur_Latn",
|
61 |
+
"fuv_Latn",
|
62 |
+
"gla_Latn",
|
63 |
+
"gle_Latn",
|
64 |
+
"glg_Latn",
|
65 |
+
"grn_Latn",
|
66 |
+
"guj_Gujr",
|
67 |
+
"hat_Latn",
|
68 |
+
"hau_Latn",
|
69 |
+
"heb_Hebr",
|
70 |
+
"hin_Deva",
|
71 |
+
"hne_Deva",
|
72 |
+
"hrv_Latn",
|
73 |
+
"hun_Latn",
|
74 |
+
"hye_Armn",
|
75 |
+
"ibo_Latn",
|
76 |
+
"ilo_Latn",
|
77 |
+
"ind_Latn",
|
78 |
+
"isl_Latn",
|
79 |
+
"ita_Latn",
|
80 |
+
"jav_Latn",
|
81 |
+
"jpn_Jpan",
|
82 |
+
"kab_Latn",
|
83 |
+
"kac_Latn",
|
84 |
+
"kam_Latn",
|
85 |
+
"kan_Knda",
|
86 |
+
"kas_Arab",
|
87 |
+
"kas_Deva",
|
88 |
+
"kat_Geor",
|
89 |
+
"knc_Arab",
|
90 |
+
"knc_Latn",
|
91 |
+
"kaz_Cyrl",
|
92 |
+
"kbp_Latn",
|
93 |
+
"kea_Latn",
|
94 |
+
"khm_Khmr",
|
95 |
+
"kik_Latn",
|
96 |
+
"kin_Latn",
|
97 |
+
"kir_Cyrl",
|
98 |
+
"kmb_Latn",
|
99 |
+
"kon_Latn",
|
100 |
+
"kor_Hang",
|
101 |
+
"kmr_Latn",
|
102 |
+
"lao_Laoo",
|
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>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
219 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,33 +1,24 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"bos_token":
|
|
|
|
|
|
|
4 |
"__type": "AddedToken",
|
5 |
-
"content": "
|
6 |
-
"lstrip":
|
7 |
"normalized": true,
|
8 |
"rstrip": false,
|
9 |
"single_word": false
|
10 |
},
|
11 |
-
"
|
12 |
-
"
|
13 |
-
"
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
"errors": "replace",
|
22 |
-
"model_max_length": 77,
|
23 |
-
"pad_token": "<|endoftext|>",
|
24 |
-
"tokenizer_class": "CLIPTokenizer",
|
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 |
+
"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/nllb-200-distilled-600M",
|
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": "NllbTokenizer",
|
23 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
}
|