Upload tokenizer

sentencepiece.bpe.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34727325a68a6a1e8580bf1e33934313f5f232bc92448d5ff77a5a850f25dbaa
-size 240462
+oid sha256:bc579c42f174c74d5a56bc4a02e6eef7759711b9415d2fd1bf4810683bdb69c5
+size 240450

special_tokens_map.json

@@ -1,7 +1,7 @@
 {
   "additional_special_tokens": [
-    "ቊ",
-    "ar_AR"
+    "ar_AR",
+    "cs_CZ"
   ],
   "bos_token": "<s>",
   "cls_token": "<s>",

tokenizer_config.json

@@ -32,7 +32,7 @@
       "single_word": false,
       "special": true
     },
-    "235": {
+    "234": {
       "content": "ar_AR",
       "lstrip": false,
       "normalized": false,
@@ -40,7 +40,7 @@
       "single_word": false,
       "special": true
     },
-    "236": {
+    "235": {
       "content": "cs_CZ",
       "lstrip": false,
       "normalized": false,
@@ -48,7 +48,7 @@
       "single_word": false,
       "special": true
     },
-    "237": {
+    "236": {
       "content": "de_DE",
       "lstrip": false,
       "normalized": false,
@@ -56,7 +56,7 @@
       "single_word": false,
       "special": true
     },
-    "238": {
+    "237": {
       "content": "en_XX",
       "lstrip": false,
       "normalized": false,
@@ -64,7 +64,7 @@
       "single_word": false,
       "special": true
     },
-    "239": {
+    "238": {
       "content": "es_XX",
       "lstrip": false,
       "normalized": false,
@@ -72,7 +72,7 @@
       "single_word": false,
       "special": true
     },
-    "240": {
+    "239": {
       "content": "et_EE",
       "lstrip": false,
       "normalized": false,
@@ -80,7 +80,7 @@
       "single_word": false,
       "special": true
     },
-    "241": {
+    "240": {
       "content": "fi_FI",
       "lstrip": false,
       "normalized": false,
@@ -88,7 +88,7 @@
       "single_word": false,
       "special": true
     },
-    "242": {
+    "241": {
       "content": "fr_XX",
       "lstrip": false,
       "normalized": false,
@@ -96,7 +96,7 @@
       "single_word": false,
       "special": true
     },
-    "243": {
+    "242": {
       "content": "gu_IN",
       "lstrip": false,
       "normalized": false,
@@ -104,7 +104,7 @@
       "single_word": false,
       "special": true
     },
-    "244": {
+    "243": {
       "content": "hi_IN",
       "lstrip": false,
       "normalized": false,
@@ -112,7 +112,7 @@
       "single_word": false,
       "special": true
     },
-    "245": {
+    "244": {
       "content": "it_IT",
       "lstrip": false,
       "normalized": false,
@@ -120,7 +120,7 @@
       "single_word": false,
       "special": true
     },
-    "246": {
+    "245": {
       "content": "ja_XX",
       "lstrip": false,
       "normalized": false,
@@ -128,7 +128,7 @@
       "single_word": false,
       "special": true
     },
-    "247": {
+    "246": {
       "content": "kk_KZ",
       "lstrip": false,
       "normalized": false,
@@ -136,7 +136,7 @@
       "single_word": false,
       "special": true
     },
-    "248": {
+    "247": {
       "content": "ko_KR",
       "lstrip": false,
       "normalized": false,
@@ -144,7 +144,7 @@
       "single_word": false,
       "special": true
     },
-    "249": {
+    "248": {
       "content": "lt_LT",
       "lstrip": false,
       "normalized": false,
@@ -152,7 +152,7 @@
       "single_word": false,
       "special": true
     },
-    "250": {
+    "249": {
       "content": "lv_LV",
       "lstrip": false,
       "normalized": false,
@@ -160,7 +160,7 @@
       "single_word": false,
       "special": true
     },
-    "251": {
+    "250": {
       "content": "my_MM",
       "lstrip": false,
       "normalized": false,
@@ -168,7 +168,7 @@
       "single_word": false,
       "special": true
     },
-    "252": {
+    "251": {
       "content": "ne_NP",
       "lstrip": false,
       "normalized": false,
@@ -176,7 +176,7 @@
       "single_word": false,
       "special": true
     },
-    "253": {
+    "252": {
       "content": "nl_XX",
       "lstrip": false,
       "normalized": false,
@@ -184,7 +184,7 @@
       "single_word": false,
       "special": true
     },
-    "254": {
+    "253": {
       "content": "ro_RO",
       "lstrip": false,
       "normalized": false,
@@ -192,7 +192,7 @@
       "single_word": false,
       "special": true
     },
-    "255": {
+    "254": {
       "content": "ru_RU",
       "lstrip": false,
       "normalized": false,
@@ -200,7 +200,7 @@
       "single_word": false,
       "special": true
     },
-    "256": {
+    "255": {
       "content": "si_LK",
       "lstrip": false,
       "normalized": false,
@@ -208,7 +208,7 @@
       "single_word": false,
       "special": true
     },
-    "257": {
+    "256": {
       "content": "tr_TR",
       "lstrip": false,
       "normalized": false,
@@ -216,7 +216,7 @@
       "single_word": false,
       "special": true
     },
-    "258": {
+    "257": {
       "content": "vi_VN",
       "lstrip": false,
       "normalized": false,
@@ -224,7 +224,7 @@
       "single_word": false,
       "special": true
     },
-    "259": {
+    "258": {
       "content": "zh_CN",
       "lstrip": false,
       "normalized": false,
@@ -234,8 +234,8 @@
     }
   },
   "additional_special_tokens": [
-    "ቊ",
-    "ar_AR"
+    "ar_AR",
+    "cs_CZ"
   ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,