Upload tokenizer

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14bb8dfb35c0ffdea7bc01e56cea38b9e3d5efcdcb9c251d6b40538e1aab555a
+size 4852054

special_tokens_map.json

@@ -1,20 +1,252 @@
 {
+  "additional_special_tokens": [
+    "ace_Arab",
+    "ace_Latn",
+    "acm_Arab",
+    "acq_Arab",
+    "aeb_Arab",
+    "afr_Latn",
+    "ajp_Arab",
+    "aka_Latn",
+    "amh_Ethi",
+    "apc_Arab",
+    "arb_Arab",
+    "ars_Arab",
+    "ary_Arab",
+    "arz_Arab",
+    "asm_Beng",
+    "ast_Latn",
+    "awa_Deva",
+    "ayr_Latn",
+    "azb_Arab",
+    "azj_Latn",
+    "bak_Cyrl",
+    "bam_Latn",
+    "ban_Latn",
+    "bel_Cyrl",
+    "bem_Latn",
+    "ben_Beng",
+    "bho_Deva",
+    "bjn_Arab",
+    "bjn_Latn",
+    "bod_Tibt",
+    "bos_Latn",
+    "bug_Latn",
+    "bul_Cyrl",
+    "cat_Latn",
+    "ceb_Latn",
+    "ces_Latn",
+    "cjk_Latn",
+    "ckb_Arab",
+    "crh_Latn",
+    "cym_Latn",
+    "dan_Latn",
+    "deu_Latn",
+    "dik_Latn",
+    "dyu_Latn",
+    "dzo_Tibt",
+    "ell_Grek",
+    "eng_Latn",
+    "epo_Latn",
+    "est_Latn",
+    "eus_Latn",
+    "ewe_Latn",
+    "fao_Latn",
+    "pes_Arab",
+    "fij_Latn",
+    "fin_Latn",
+    "fon_Latn",
+    "fra_Latn",
+    "fur_Latn",
+    "fuv_Latn",
+    "gla_Latn",
+    "gle_Latn",
+    "glg_Latn",
+    "grn_Latn",
+    "guj_Gujr",
+    "hat_Latn",
+    "hau_Latn",
+    "heb_Hebr",
+    "hin_Deva",
+    "hne_Deva",
+    "hrv_Latn",
+    "hun_Latn",
+    "hye_Armn",
+    "ibo_Latn",
+    "ilo_Latn",
+    "ind_Latn",
+    "isl_Latn",
+    "ita_Latn",
+    "jav_Latn",
+    "jpn_Jpan",
+    "kab_Latn",
+    "kac_Latn",
+    "kam_Latn",
+    "kan_Knda",
+    "kas_Arab",
+    "kas_Deva",
+    "kat_Geor",
+    "knc_Arab",
+    "knc_Latn",
+    "kaz_Cyrl",
+    "kbp_Latn",
+    "kea_Latn",
+    "khm_Khmr",
+    "kik_Latn",
+    "kin_Latn",
+    "kir_Cyrl",
+    "kmb_Latn",
+    "kon_Latn",
+    "kor_Hang",
+    "kmr_Latn",
+    "lao_Laoo",
+    "lvs_Latn",
+    "lij_Latn",
+    "lim_Latn",
+    "lin_Latn",
+    "lit_Latn",
+    "lmo_Latn",
+    "ltg_Latn",
+    "ltz_Latn",
+    "lua_Latn",
+    "lug_Latn",
+    "luo_Latn",
+    "lus_Latn",
+    "mag_Deva",
+    "mai_Deva",
+    "mal_Mlym",
+    "mar_Deva",
+    "min_Latn",
+    "mkd_Cyrl",
+    "plt_Latn",
+    "mlt_Latn",
+    "mni_Beng",
+    "khk_Cyrl",
+    "mos_Latn",
+    "mri_Latn",
+    "zsm_Latn",
+    "mya_Mymr",
+    "nld_Latn",
+    "nno_Latn",
+    "nob_Latn",
+    "npi_Deva",
+    "nso_Latn",
+    "nus_Latn",
+    "nya_Latn",
+    "oci_Latn",
+    "gaz_Latn",
+    "ory_Orya",
+    "pag_Latn",
+    "pan_Guru",
+    "pap_Latn",
+    "pol_Latn",
+    "por_Latn",
+    "prs_Arab",
+    "pbt_Arab",
+    "quy_Latn",
+    "ron_Latn",
+    "run_Latn",
+    "rus_Cyrl",
+    "sag_Latn",
+    "san_Deva",
+    "sat_Beng",
+    "scn_Latn",
+    "shn_Mymr",
+    "sin_Sinh",
+    "slk_Latn",
+    "slv_Latn",
+    "smo_Latn",
+    "sna_Latn",
+    "snd_Arab",
+    "som_Latn",
+    "sot_Latn",
+    "spa_Latn",
+    "als_Latn",
+    "srd_Latn",
+    "srp_Cyrl",
+    "ssw_Latn",
+    "sun_Latn",
+    "swe_Latn",
+    "swh_Latn",
+    "szl_Latn",
+    "tam_Taml",
+    "tat_Cyrl",
+    "tel_Telu",
+    "tgk_Cyrl",
+    "tgl_Latn",
+    "tha_Thai",
+    "tir_Ethi",
+    "taq_Latn",
+    "taq_Tfng",
+    "tpi_Latn",
+    "tsn_Latn",
+    "tso_Latn",
+    "tuk_Latn",
+    "tum_Latn",
+    "tur_Latn",
+    "twi_Latn",
+    "tzm_Tfng",
+    "uig_Arab",
+    "ukr_Cyrl",
+    "umb_Latn",
+    "urd_Arab",
+    "uzn_Latn",
+    "vec_Latn",
+    "vie_Latn",
+    "war_Latn",
+    "wol_Latn",
+    "xho_Latn",
+    "ydd_Hebr",
+    "yor_Latn",
+    "yue_Hant",
+    "zho_Hans",
+    "zho_Hant",
+    "zul_Latn"
+  ],
   "bos_token": {
-    "content": "<|begin_of_text|>",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|end_of_text|>",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "pad_token": {
-    "content": "<|reserved_special_token_250|>",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -1,2063 +1,1883 @@
 {
   "added_tokens_decoder": {
-    "128000": {
-      "content": "<|begin_of_text|>",
+    "0": {
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128001": {
-      "content": "<|end_of_text|>",
+    "1": {
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128002": {
-      "content": "<|reserved_special_token_0|>",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128003": {
-      "content": "<|reserved_special_token_1|>",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128004": {
-      "content": "<|reserved_special_token_2|>",
+    "256001": {
+      "content": "ace_Arab",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128005": {
-      "content": "<|reserved_special_token_3|>",
+    "256002": {
+      "content": "ace_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128006": {
-      "content": "<|start_header_id|>",
+    "256003": {
+      "content": "acm_Arab",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128007": {
-      "content": "<|end_header_id|>",
+    "256004": {
+      "content": "acq_Arab",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128008": {
-      "content": "<|reserved_special_token_4|>",
+    "256005": {
+      "content": "aeb_Arab",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128009": {
-      "content": "<|eot_id|>",
+    "256006": {
+      "content": "afr_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128010": {
-      "content": "<|reserved_special_token_5|>",
+    "256007": {
+      "content": "ajp_Arab",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128011": {
-      "content": "<|reserved_special_token_6|>",
+    "256008": {
+      "content": "aka_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128012": {
-      "content": "<|reserved_special_token_7|>",
+    "256009": {
+      "content": "amh_Ethi",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128013": {
-      "content": "<|reserved_special_token_8|>",
+    "256010": {
+      "content": "apc_Arab",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128014": {
-      "content": "<|reserved_special_token_9|>",
+    "256011": {
+      "content": "arb_Arab",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128015": {
-      "content": "<|reserved_special_token_10|>",
+    "256012": {
+      "content": "ars_Arab",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128016": {
-      "content": "<|reserved_special_token_11|>",
+    "256013": {
+      "content": "ary_Arab",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128017": {
-      "content": "<|reserved_special_token_12|>",
+    "256014": {
+      "content": "arz_Arab",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128018": {
-      "content": "<|reserved_special_token_13|>",
+    "256015": {
+      "content": "asm_Beng",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128019": {
-      "content": "<|reserved_special_token_14|>",
+    "256016": {
+      "content": "ast_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128020": {
-      "content": "<|reserved_special_token_15|>",
+    "256017": {
+      "content": "awa_Deva",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128021": {
-      "content": "<|reserved_special_token_16|>",
+    "256018": {
+      "content": "ayr_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128022": {
-      "content": "<|reserved_special_token_17|>",
+    "256019": {
+      "content": "azb_Arab",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128023": {
-      "content": "<|reserved_special_token_18|>",
+    "256020": {
+      "content": "azj_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128024": {
-      "content": "<|reserved_special_token_19|>",
+    "256021": {
+      "content": "bak_Cyrl",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128025": {
-      "content": "<|reserved_special_token_20|>",
+    "256022": {
+      "content": "bam_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128026": {
-      "content": "<|reserved_special_token_21|>",
+    "256023": {
+      "content": "ban_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128027": {
-      "content": "<|reserved_special_token_22|>",
+    "256024": {
+      "content": "bel_Cyrl",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128028": {
-      "content": "<|reserved_special_token_23|>",
+    "256025": {
+      "content": "bem_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128029": {
-      "content": "<|reserved_special_token_24|>",
+    "256026": {
+      "content": "ben_Beng",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128030": {
-      "content": "<|reserved_special_token_25|>",
+    "256027": {
+      "content": "bho_Deva",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128031": {
-      "content": "<|reserved_special_token_26|>",
+    "256028": {
+      "content": "bjn_Arab",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128032": {
-      "content": "<|reserved_special_token_27|>",
+    "256029": {
+      "content": "bjn_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128033": {
-      "content": "<|reserved_special_token_28|>",
+    "256030": {
+      "content": "bod_Tibt",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128034": {
-      "content": "<|reserved_special_token_29|>",
+    "256031": {
+      "content": "bos_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128035": {
-      "content": "<|reserved_special_token_30|>",
+    "256032": {
+      "content": "bug_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128036": {
-      "content": "<|reserved_special_token_31|>",
+    "256033": {
+      "content": "bul_Cyrl",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128037": {
-      "content": "<|reserved_special_token_32|>",
+    "256034": {
+      "content": "cat_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128038": {
-      "content": "<|reserved_special_token_33|>",
+    "256035": {
+      "content": "ceb_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128039": {
-      "content": "<|reserved_special_token_34|>",
+    "256036": {
+      "content": "ces_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128040": {
-      "content": "<|reserved_special_token_35|>",
+    "256037": {
+      "content": "cjk_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128041": {
-      "content": "<|reserved_special_token_36|>",
+    "256038": {
+      "content": "ckb_Arab",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128042": {
-      "content": "<|reserved_special_token_37|>",
+    "256039": {
+      "content": "crh_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128043": {
-      "content": "<|reserved_special_token_38|>",
+    "256040": {
+      "content": "cym_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128044": {
-      "content": "<|reserved_special_token_39|>",
+    "256041": {
+      "content": "dan_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128045": {
-      "content": "<|reserved_special_token_40|>",
+    "256042": {
+      "content": "deu_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128046": {
-      "content": "<|reserved_special_token_41|>",
+    "256043": {
+      "content": "dik_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128047": {
-      "content": "<|reserved_special_token_42|>",
+    "256044": {
+      "content": "dyu_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128048": {
-      "content": "<|reserved_special_token_43|>",
+    "256045": {
+      "content": "dzo_Tibt",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128049": {
-      "content": "<|reserved_special_token_44|>",
+    "256046": {
+      "content": "ell_Grek",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128050": {
-      "content": "<|reserved_special_token_45|>",
+    "256047": {
+      "content": "eng_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128051": {
-      "content": "<|reserved_special_token_46|>",
+    "256048": {
+      "content": "epo_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128052": {
-      "content": "<|reserved_special_token_47|>",
+    "256049": {
+      "content": "est_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128053": {
-      "content": "<|reserved_special_token_48|>",
+    "256050": {
+      "content": "eus_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128054": {
-      "content": "<|reserved_special_token_49|>",
+    "256051": {
+      "content": "ewe_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128055": {
-      "content": "<|reserved_special_token_50|>",
+    "256052": {
+      "content": "fao_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128056": {
-      "content": "<|reserved_special_token_51|>",
+    "256053": {
+      "content": "pes_Arab",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128057": {
-      "content": "<|reserved_special_token_52|>",
+    "256054": {
+      "content": "fij_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128058": {
-      "content": "<|reserved_special_token_53|>",
+    "256055": {
+      "content": "fin_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128059": {
-      "content": "<|reserved_special_token_54|>",
+    "256056": {
+      "content": "fon_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128060": {
-      "content": "<|reserved_special_token_55|>",
+    "256057": {
+      "content": "fra_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128061": {
-      "content": "<|reserved_special_token_56|>",
+    "256058": {
+      "content": "fur_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128062": {
-      "content": "<|reserved_special_token_57|>",
+    "256059": {
+      "content": "fuv_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128063": {
-      "content": "<|reserved_special_token_58|>",
+    "256060": {
+      "content": "gla_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128064": {
-      "content": "<|reserved_special_token_59|>",
+    "256061": {
+      "content": "gle_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128065": {
-      "content": "<|reserved_special_token_60|>",
+    "256062": {
+      "content": "glg_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128066": {
-      "content": "<|reserved_special_token_61|>",
+    "256063": {
+      "content": "grn_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128067": {
-      "content": "<|reserved_special_token_62|>",
+    "256064": {
+      "content": "guj_Gujr",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128068": {
-      "content": "<|reserved_special_token_63|>",
+    "256065": {
+      "content": "hat_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128069": {
-      "content": "<|reserved_special_token_64|>",
+    "256066": {
+      "content": "hau_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128070": {
-      "content": "<|reserved_special_token_65|>",
+    "256067": {
+      "content": "heb_Hebr",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128071": {
-      "content": "<|reserved_special_token_66|>",
+    "256068": {
+      "content": "hin_Deva",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128072": {
-      "content": "<|reserved_special_token_67|>",
+    "256069": {
+      "content": "hne_Deva",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128073": {
-      "content": "<|reserved_special_token_68|>",
+    "256070": {
+      "content": "hrv_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128074": {
-      "content": "<|reserved_special_token_69|>",
+    "256071": {
+      "content": "hun_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128075": {
-      "content": "<|reserved_special_token_70|>",
+    "256072": {
+      "content": "hye_Armn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128076": {
-      "content": "<|reserved_special_token_71|>",
+    "256073": {
+      "content": "ibo_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128077": {
-      "content": "<|reserved_special_token_72|>",
+    "256074": {
+      "content": "ilo_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128078": {
-      "content": "<|reserved_special_token_73|>",
+    "256075": {
+      "content": "ind_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128079": {
-      "content": "<|reserved_special_token_74|>",
+    "256076": {
+      "content": "isl_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128080": {
-      "content": "<|reserved_special_token_75|>",
+    "256077": {
+      "content": "ita_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128081": {
-      "content": "<|reserved_special_token_76|>",
+    "256078": {
+      "content": "jav_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128082": {
-      "content": "<|reserved_special_token_77|>",
+    "256079": {
+      "content": "jpn_Jpan",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128083": {
-      "content": "<|reserved_special_token_78|>",
+    "256080": {
+      "content": "kab_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128084": {
-      "content": "<|reserved_special_token_79|>",
+    "256081": {
+      "content": "kac_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128085": {
-      "content": "<|reserved_special_token_80|>",
+    "256082": {
+      "content": "kam_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128086": {
-      "content": "<|reserved_special_token_81|>",
+    "256083": {
+      "content": "kan_Knda",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128087": {
-      "content": "<|reserved_special_token_82|>",
+    "256084": {
+      "content": "kas_Arab",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128088": {
-      "content": "<|reserved_special_token_83|>",
+    "256085": {
+      "content": "kas_Deva",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128089": {
-      "content": "<|reserved_special_token_84|>",
+    "256086": {
+      "content": "kat_Geor",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128090": {
-      "content": "<|reserved_special_token_85|>",
+    "256087": {
+      "content": "knc_Arab",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128091": {
-      "content": "<|reserved_special_token_86|>",
+    "256088": {
+      "content": "knc_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128092": {
-      "content": "<|reserved_special_token_87|>",
+    "256089": {
+      "content": "kaz_Cyrl",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128093": {
-      "content": "<|reserved_special_token_88|>",
+    "256090": {
+      "content": "kbp_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128094": {
-      "content": "<|reserved_special_token_89|>",
+    "256091": {
+      "content": "kea_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128095": {
-      "content": "<|reserved_special_token_90|>",
+    "256092": {
+      "content": "khm_Khmr",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128096": {
-      "content": "<|reserved_special_token_91|>",
+    "256093": {
+      "content": "kik_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128097": {
-      "content": "<|reserved_special_token_92|>",
+    "256094": {
+      "content": "kin_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128098": {
-      "content": "<|reserved_special_token_93|>",
+    "256095": {
+      "content": "kir_Cyrl",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128099": {
-      "content": "<|reserved_special_token_94|>",
+    "256096": {
+      "content": "kmb_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128100": {
-      "content": "<|reserved_special_token_95|>",
+    "256097": {
+      "content": "kon_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128101": {
-      "content": "<|reserved_special_token_96|>",
+    "256098": {
+      "content": "kor_Hang",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128102": {
-      "content": "<|reserved_special_token_97|>",
+    "256099": {
+      "content": "kmr_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128103": {
-      "content": "<|reserved_special_token_98|>",
+    "256100": {
+      "content": "lao_Laoo",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128104": {
-      "content": "<|reserved_special_token_99|>",
+    "256101": {
+      "content": "lvs_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128105": {
-      "content": "<|reserved_special_token_100|>",
+    "256102": {
+      "content": "lij_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128106": {
-      "content": "<|reserved_special_token_101|>",
+    "256103": {
+      "content": "lim_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128107": {
-      "content": "<|reserved_special_token_102|>",
+    "256104": {
+      "content": "lin_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128108": {
-      "content": "<|reserved_special_token_103|>",
+    "256105": {
+      "content": "lit_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128109": {
-      "content": "<|reserved_special_token_104|>",
+    "256106": {
+      "content": "lmo_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128110": {
-      "content": "<|reserved_special_token_105|>",
+    "256107": {
+      "content": "ltg_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128111": {
-      "content": "<|reserved_special_token_106|>",
+    "256108": {
+      "content": "ltz_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128112": {
-      "content": "<|reserved_special_token_107|>",
+    "256109": {
+      "content": "lua_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128113": {
-      "content": "<|reserved_special_token_108|>",
+    "256110": {
+      "content": "lug_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128114": {
-      "content": "<|reserved_special_token_109|>",
+    "256111": {
+      "content": "luo_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128115": {
-      "content": "<|reserved_special_token_110|>",
+    "256112": {
+      "content": "lus_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128116": {
-      "content": "<|reserved_special_token_111|>",
+    "256113": {
+      "content": "mag_Deva",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128117": {
-      "content": "<|reserved_special_token_112|>",
+    "256114": {
+      "content": "mai_Deva",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128118": {
-      "content": "<|reserved_special_token_113|>",
+    "256115": {
+      "content": "mal_Mlym",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128119": {
-      "content": "<|reserved_special_token_114|>",
+    "256116": {
+      "content": "mar_Deva",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128120": {
-      "content": "<|reserved_special_token_115|>",
+    "256117": {
+      "content": "min_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128121": {
-      "content": "<|reserved_special_token_116|>",
+    "256118": {
+      "content": "mkd_Cyrl",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128122": {
-      "content": "<|reserved_special_token_117|>",
+    "256119": {
+      "content": "plt_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128123": {
-      "content": "<|reserved_special_token_118|>",
+    "256120": {
+      "content": "mlt_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128124": {
-      "content": "<|reserved_special_token_119|>",
+    "256121": {
+      "content": "mni_Beng",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128125": {
-      "content": "<|reserved_special_token_120|>",
+    "256122": {
+      "content": "khk_Cyrl",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128126": {
-      "content": "<|reserved_special_token_121|>",
+    "256123": {
+      "content": "mos_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128127": {
-      "content": "<|reserved_special_token_122|>",
+    "256124": {
+      "content": "mri_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128128": {
-      "content": "<|reserved_special_token_123|>",
+    "256125": {
+      "content": "zsm_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128129": {
-      "content": "<|reserved_special_token_124|>",
+    "256126": {
+      "content": "mya_Mymr",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128130": {
-      "content": "<|reserved_special_token_125|>",
+    "256127": {
+      "content": "nld_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128131": {
-      "content": "<|reserved_special_token_126|>",
+    "256128": {
+      "content": "nno_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128132": {
-      "content": "<|reserved_special_token_127|>",
+    "256129": {
+      "content": "nob_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128133": {
-      "content": "<|reserved_special_token_128|>",
+    "256130": {
+      "content": "npi_Deva",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128134": {
-      "content": "<|reserved_special_token_129|>",
+    "256131": {
+      "content": "nso_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128135": {
-      "content": "<|reserved_special_token_130|>",
+    "256132": {
+      "content": "nus_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128136": {
-      "content": "<|reserved_special_token_131|>",
+    "256133": {
+      "content": "nya_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128137": {
-      "content": "<|reserved_special_token_132|>",
+    "256134": {
+      "content": "oci_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128138": {
-      "content": "<|reserved_special_token_133|>",
+    "256135": {
+      "content": "gaz_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128139": {
-      "content": "<|reserved_special_token_134|>",
+    "256136": {
+      "content": "ory_Orya",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128140": {
-      "content": "<|reserved_special_token_135|>",
+    "256137": {
+      "content": "pag_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128141": {
-      "content": "<|reserved_special_token_136|>",
+    "256138": {
+      "content": "pan_Guru",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128142": {
-      "content": "<|reserved_special_token_137|>",
+    "256139": {
+      "content": "pap_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128143": {
-      "content": "<|reserved_special_token_138|>",
+    "256140": {
+      "content": "pol_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128144": {
-      "content": "<|reserved_special_token_139|>",
+    "256141": {
+      "content": "por_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128145": {
-      "content": "<|reserved_special_token_140|>",
+    "256142": {
+      "content": "prs_Arab",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128146": {
-      "content": "<|reserved_special_token_141|>",
+    "256143": {
+      "content": "pbt_Arab",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128147": {
-      "content": "<|reserved_special_token_142|>",
+    "256144": {
+      "content": "quy_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128148": {
-      "content": "<|reserved_special_token_143|>",
+    "256145": {
+      "content": "ron_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128149": {
-      "content": "<|reserved_special_token_144|>",
+    "256146": {
+      "content": "run_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128150": {
-      "content": "<|reserved_special_token_145|>",
+    "256147": {
+      "content": "rus_Cyrl",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128151": {
-      "content": "<|reserved_special_token_146|>",
+    "256148": {
+      "content": "sag_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128152": {
-      "content": "<|reserved_special_token_147|>",
+    "256149": {
+      "content": "san_Deva",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128153": {
-      "content": "<|reserved_special_token_148|>",
+    "256150": {
+      "content": "sat_Beng",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128154": {
-      "content": "<|reserved_special_token_149|>",
+    "256151": {
+      "content": "scn_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128155": {
-      "content": "<|reserved_special_token_150|>",
+    "256152": {
+      "content": "shn_Mymr",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128156": {
-      "content": "<|reserved_special_token_151|>",
+    "256153": {
+      "content": "sin_Sinh",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128157": {
-      "content": "<|reserved_special_token_152|>",
+    "256154": {
+      "content": "slk_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128158": {
-      "content": "<|reserved_special_token_153|>",
+    "256155": {
+      "content": "slv_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128159": {
-      "content": "<|reserved_special_token_154|>",
+    "256156": {
+      "content": "smo_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128160": {
-      "content": "<|reserved_special_token_155|>",
+    "256157": {
+      "content": "sna_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128161": {
-      "content": "<|reserved_special_token_156|>",
+    "256158": {
+      "content": "snd_Arab",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128162": {
-      "content": "<|reserved_special_token_157|>",
+    "256159": {
+      "content": "som_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128163": {
-      "content": "<|reserved_special_token_158|>",
+    "256160": {
+      "content": "sot_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128164": {
-      "content": "<|reserved_special_token_159|>",
+    "256161": {
+      "content": "spa_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128165": {
-      "content": "<|reserved_special_token_160|>",
+    "256162": {
+      "content": "als_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128166": {
-      "content": "<|reserved_special_token_161|>",
+    "256163": {
+      "content": "srd_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128167": {
-      "content": "<|reserved_special_token_162|>",
+    "256164": {
+      "content": "srp_Cyrl",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128168": {
-      "content": "<|reserved_special_token_163|>",
+    "256165": {
+      "content": "ssw_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128169": {
-      "content": "<|reserved_special_token_164|>",
+    "256166": {
+      "content": "sun_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128170": {
-      "content": "<|reserved_special_token_165|>",
+    "256167": {
+      "content": "swe_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128171": {
-      "content": "<|reserved_special_token_166|>",
+    "256168": {
+      "content": "swh_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128172": {
-      "content": "<|reserved_special_token_167|>",
+    "256169": {
+      "content": "szl_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128173": {
-      "content": "<|reserved_special_token_168|>",
+    "256170": {
+      "content": "tam_Taml",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128174": {
-      "content": "<|reserved_special_token_169|>",
+    "256171": {
+      "content": "tat_Cyrl",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128175": {
-      "content": "<|reserved_special_token_170|>",
+    "256172": {
+      "content": "tel_Telu",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128176": {
-      "content": "<|reserved_special_token_171|>",
+    "256173": {
+      "content": "tgk_Cyrl",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128177": {
-      "content": "<|reserved_special_token_172|>",
+    "256174": {
+      "content": "tgl_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128178": {
-      "content": "<|reserved_special_token_173|>",
+    "256175": {
+      "content": "tha_Thai",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128179": {
-      "content": "<|reserved_special_token_174|>",
+    "256176": {
+      "content": "tir_Ethi",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128180": {
-      "content": "<|reserved_special_token_175|>",
+    "256177": {
+      "content": "taq_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128181": {
-      "content": "<|reserved_special_token_176|>",
+    "256178": {
+      "content": "taq_Tfng",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128182": {
-      "content": "<|reserved_special_token_177|>",
+    "256179": {
+      "content": "tpi_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128183": {
-      "content": "<|reserved_special_token_178|>",
+    "256180": {
+      "content": "tsn_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128184": {
-      "content": "<|reserved_special_token_179|>",
+    "256181": {
+      "content": "tso_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128185": {
-      "content": "<|reserved_special_token_180|>",
+    "256182": {
+      "content": "tuk_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128186": {
-      "content": "<|reserved_special_token_181|>",
+    "256183": {
+      "content": "tum_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128187": {
-      "content": "<|reserved_special_token_182|>",
+    "256184": {
+      "content": "tur_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128188": {
-      "content": "<|reserved_special_token_183|>",
+    "256185": {
+      "content": "twi_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128189": {
-      "content": "<|reserved_special_token_184|>",
+    "256186": {
+      "content": "tzm_Tfng",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128190": {
-      "content": "<|reserved_special_token_185|>",
+    "256187": {
+      "content": "uig_Arab",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128191": {
-      "content": "<|reserved_special_token_186|>",
+    "256188": {
+      "content": "ukr_Cyrl",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128192": {
-      "content": "<|reserved_special_token_187|>",
+    "256189": {
+      "content": "umb_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128193": {
-      "content": "<|reserved_special_token_188|>",
+    "256190": {
+      "content": "urd_Arab",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128194": {
-      "content": "<|reserved_special_token_189|>",
+    "256191": {
+      "content": "uzn_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128195": {
-      "content": "<|reserved_special_token_190|>",
+    "256192": {
+      "content": "vec_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128196": {
-      "content": "<|reserved_special_token_191|>",
+    "256193": {
+      "content": "vie_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128197": {
-      "content": "<|reserved_special_token_192|>",
+    "256194": {
+      "content": "war_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128198": {
-      "content": "<|reserved_special_token_193|>",
+    "256195": {
+      "content": "wol_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128199": {
-      "content": "<|reserved_special_token_194|>",
+    "256196": {
+      "content": "xho_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128200": {
-      "content": "<|reserved_special_token_195|>",
+    "256197": {
+      "content": "ydd_Hebr",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128201": {
-      "content": "<|reserved_special_token_196|>",
+    "256198": {
+      "content": "yor_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128202": {
-      "content": "<|reserved_special_token_197|>",
+    "256199": {
+      "content": "yue_Hant",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128203": {
-      "content": "<|reserved_special_token_198|>",
+    "256200": {
+      "content": "zho_Hans",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128204": {
-      "content": "<|reserved_special_token_199|>",
+    "256201": {
+      "content": "zho_Hant",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128205": {
-      "content": "<|reserved_special_token_200|>",
+    "256202": {
+      "content": "zul_Latn",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128206": {
-      "content": "<|reserved_special_token_201|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128207": {
-      "content": "<|reserved_special_token_202|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128208": {
-      "content": "<|reserved_special_token_203|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128209": {
-      "content": "<|reserved_special_token_204|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128210": {
-      "content": "<|reserved_special_token_205|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128211": {
-      "content": "<|reserved_special_token_206|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128212": {
-      "content": "<|reserved_special_token_207|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128213": {
-      "content": "<|reserved_special_token_208|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128214": {
-      "content": "<|reserved_special_token_209|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128215": {
-      "content": "<|reserved_special_token_210|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128216": {
-      "content": "<|reserved_special_token_211|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128217": {
-      "content": "<|reserved_special_token_212|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128218": {
-      "content": "<|reserved_special_token_213|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128219": {
-      "content": "<|reserved_special_token_214|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128220": {
-      "content": "<|reserved_special_token_215|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128221": {
-      "content": "<|reserved_special_token_216|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128222": {
-      "content": "<|reserved_special_token_217|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128223": {
-      "content": "<|reserved_special_token_218|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128224": {
-      "content": "<|reserved_special_token_219|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128225": {
-      "content": "<|reserved_special_token_220|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128226": {
-      "content": "<|reserved_special_token_221|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128227": {
-      "content": "<|reserved_special_token_222|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128228": {
-      "content": "<|reserved_special_token_223|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128229": {
-      "content": "<|reserved_special_token_224|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128230": {
-      "content": "<|reserved_special_token_225|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128231": {
-      "content": "<|reserved_special_token_226|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128232": {
-      "content": "<|reserved_special_token_227|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128233": {
-      "content": "<|reserved_special_token_228|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128234": {
-      "content": "<|reserved_special_token_229|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128235": {
-      "content": "<|reserved_special_token_230|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128236": {
-      "content": "<|reserved_special_token_231|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128237": {
-      "content": "<|reserved_special_token_232|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128238": {
-      "content": "<|reserved_special_token_233|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128239": {
-      "content": "<|reserved_special_token_234|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128240": {
-      "content": "<|reserved_special_token_235|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128241": {
-      "content": "<|reserved_special_token_236|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128242": {
-      "content": "<|reserved_special_token_237|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128243": {
-      "content": "<|reserved_special_token_238|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128244": {
-      "content": "<|reserved_special_token_239|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128245": {
-      "content": "<|reserved_special_token_240|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128246": {
-      "content": "<|reserved_special_token_241|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128247": {
-      "content": "<|reserved_special_token_242|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128248": {
-      "content": "<|reserved_special_token_243|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128249": {
-      "content": "<|reserved_special_token_244|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128250": {
-      "content": "<|reserved_special_token_245|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128251": {
-      "content": "<|reserved_special_token_246|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128252": {
-      "content": "<|reserved_special_token_247|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128253": {
-      "content": "<|reserved_special_token_248|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128254": {
-      "content": "<|reserved_special_token_249|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128255": {
-      "content": "<|reserved_special_token_250|>",
-      "lstrip": false,
-      "normalized": false,
+    "256203": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<|begin_of_text|>",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|end_of_text|>",
-  "model_input_names": [
-    "input_ids",
-    "attention_mask"
+  "additional_special_tokens": [
+    "ace_Arab",
+    "ace_Latn",
+    "acm_Arab",
+    "acq_Arab",
+    "aeb_Arab",
+    "afr_Latn",
+    "ajp_Arab",
+    "aka_Latn",
+    "amh_Ethi",
+    "apc_Arab",
+    "arb_Arab",
+    "ars_Arab",
+    "ary_Arab",
+    "arz_Arab",
+    "asm_Beng",
+    "ast_Latn",
+    "awa_Deva",
+    "ayr_Latn",
+    "azb_Arab",
+    "azj_Latn",
+    "bak_Cyrl",
+    "bam_Latn",
+    "ban_Latn",
+    "bel_Cyrl",
+    "bem_Latn",
+    "ben_Beng",
+    "bho_Deva",
+    "bjn_Arab",
+    "bjn_Latn",
+    "bod_Tibt",
+    "bos_Latn",
+    "bug_Latn",
+    "bul_Cyrl",
+    "cat_Latn",
+    "ceb_Latn",
+    "ces_Latn",
+    "cjk_Latn",
+    "ckb_Arab",
+    "crh_Latn",
+    "cym_Latn",
+    "dan_Latn",
+    "deu_Latn",
+    "dik_Latn",
+    "dyu_Latn",
+    "dzo_Tibt",
+    "ell_Grek",
+    "eng_Latn",
+    "epo_Latn",
+    "est_Latn",
+    "eus_Latn",
+    "ewe_Latn",
+    "fao_Latn",
+    "pes_Arab",
+    "fij_Latn",
+    "fin_Latn",
+    "fon_Latn",
+    "fra_Latn",
+    "fur_Latn",
+    "fuv_Latn",
+    "gla_Latn",
+    "gle_Latn",
+    "glg_Latn",
+    "grn_Latn",
+    "guj_Gujr",
+    "hat_Latn",
+    "hau_Latn",
+    "heb_Hebr",
+    "hin_Deva",
+    "hne_Deva",
+    "hrv_Latn",
+    "hun_Latn",
+    "hye_Armn",
+    "ibo_Latn",
+    "ilo_Latn",
+    "ind_Latn",
+    "isl_Latn",
+    "ita_Latn",
+    "jav_Latn",
+    "jpn_Jpan",
+    "kab_Latn",
+    "kac_Latn",
+    "kam_Latn",
+    "kan_Knda",
+    "kas_Arab",
+    "kas_Deva",
+    "kat_Geor",
+    "knc_Arab",
+    "knc_Latn",
+    "kaz_Cyrl",
+    "kbp_Latn",
+    "kea_Latn",
+    "khm_Khmr",
+    "kik_Latn",
+    "kin_Latn",
+    "kir_Cyrl",
+    "kmb_Latn",
+    "kon_Latn",
+    "kor_Hang",
+    "kmr_Latn",
+    "lao_Laoo",
+    "lvs_Latn",
+    "lij_Latn",
+    "lim_Latn",
+    "lin_Latn",
+    "lit_Latn",
+    "lmo_Latn",
+    "ltg_Latn",
+    "ltz_Latn",
+    "lua_Latn",
+    "lug_Latn",
+    "luo_Latn",
+    "lus_Latn",
+    "mag_Deva",
+    "mai_Deva",
+    "mal_Mlym",
+    "mar_Deva",
+    "min_Latn",
+    "mkd_Cyrl",
+    "plt_Latn",
+    "mlt_Latn",
+    "mni_Beng",
+    "khk_Cyrl",
+    "mos_Latn",
+    "mri_Latn",
+    "zsm_Latn",
+    "mya_Mymr",
+    "nld_Latn",
+    "nno_Latn",
+    "nob_Latn",
+    "npi_Deva",
+    "nso_Latn",
+    "nus_Latn",
+    "nya_Latn",
+    "oci_Latn",
+    "gaz_Latn",
+    "ory_Orya",
+    "pag_Latn",
+    "pan_Guru",
+    "pap_Latn",
+    "pol_Latn",
+    "por_Latn",
+    "prs_Arab",
+    "pbt_Arab",
+    "quy_Latn",
+    "ron_Latn",
+    "run_Latn",
+    "rus_Cyrl",
+    "sag_Latn",
+    "san_Deva",
+    "sat_Beng",
+    "scn_Latn",
+    "shn_Mymr",
+    "sin_Sinh",
+    "slk_Latn",
+    "slv_Latn",
+    "smo_Latn",
+    "sna_Latn",
+    "snd_Arab",
+    "som_Latn",
+    "sot_Latn",
+    "spa_Latn",
+    "als_Latn",
+    "srd_Latn",
+    "srp_Cyrl",
+    "ssw_Latn",
+    "sun_Latn",
+    "swe_Latn",
+    "swh_Latn",
+    "szl_Latn",
+    "tam_Taml",
+    "tat_Cyrl",
+    "tel_Telu",
+    "tgk_Cyrl",
+    "tgl_Latn",
+    "tha_Thai",
+    "tir_Ethi",
+    "taq_Latn",
+    "taq_Tfng",
+    "tpi_Latn",
+    "tsn_Latn",
+    "tso_Latn",
+    "tuk_Latn",
+    "tum_Latn",
+    "tur_Latn",
+    "twi_Latn",
+    "tzm_Tfng",
+    "uig_Arab",
+    "ukr_Cyrl",
+    "umb_Latn",
+    "urd_Arab",
+    "uzn_Latn",
+    "vec_Latn",
+    "vie_Latn",
+    "war_Latn",
+    "wol_Latn",
+    "xho_Latn",
+    "ydd_Hebr",
+    "yor_Latn",
+    "yue_Hant",
+    "zho_Hans",
+    "zho_Hant",
+    "zul_Latn"
   ],
-  "model_max_length": 8192,
-  "pad_token": "<|reserved_special_token_250|>",
-  "padding_side": "left",
-  "tokenizer_class": "PreTrainedTokenizerFast"
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "legacy_behaviour": false,
+  "mask_token": "<mask>",
+  "max_length": 200,
+  "model_max_length": 1024,
+  "num_labels": 2,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "src_lang": "mal_Mlym",
+  "stride": 0,
+  "tgt_lang": "eng_Latn",
+  "tokenizer_class": "NllbTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
 }