Upload tokenizer

special_tokens_map.json

@@ -1,7 +1,9 @@
 {
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": "<mask>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
+  "bos_token": "[BOS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[EOS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenization.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff30dc12b46871e024d8592e6d360e0bcd41733a2ffd3dd30cd2aa393d6b751b
-size 248649
+oid sha256:69db0f27962663caa548cf3f946a029813d752e2f4c2be4946b0547db10bd7b0
+size 248674

tokenizer.json

@@ -5,7 +5,7 @@
   "added_tokens": [
     {
       "id": 0,
-      "content": "<pad>",
+      "content": "[PAD]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -14,7 +14,7 @@
     },
     {
       "id": 1,
-      "content": "<unk>",
+      "content": "[UNK]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -23,7 +23,7 @@
     },
     {
       "id": 2,
-      "content": "<s>",
+      "content": "[BOS]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -32,7 +32,7 @@
     },
     {
       "id": 3,
-      "content": "</s>",
+      "content": "[EOS]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -41,7 +41,25 @@
     },
     {
       "id": 4,
-      "content": "<mask>",
+      "content": "[CLS]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 5,
+      "content": "[SEP]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 6,
+      "content": "[MASK]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -88,23 +106,31 @@
     "unk_id": 1,
     "vocab": [
       [
-        "<pad>",
+        "[PAD]",
+        0.0
+      ],
+      [
+        "[UNK]",
+        0.0
+      ],
+      [
+        "[BOS]",
         0.0
       ],
       [
-        "<unk>",
+        "[EOS]",
         0.0
       ],
       [
-        "<s>",
+        "[CLS]",
         0.0
       ],
       [
-        "</s>",
+        "[SEP]",
         0.0
       ],
       [
-        "<mask>",
+        "[MASK]",
         0.0
       ],
       [
@@ -3163,14 +3189,6 @@
         "▁agbaza",
         -9.1220121383667
       ],
-      [
-        "aguidi",
-        -9.122014045715332
-      ],
-      [
-        "▁iglej",
-        -9.122014999389648
-      ],
       [
         "’",
         -9.184510231018066

tokenizer_config.json

@@ -4,7 +4,7 @@
   "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
-      "content": "<pad>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -12,7 +12,7 @@
       "special": true
     },
     "1": {
-      "content": "<unk>",
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -20,7 +20,7 @@
       "special": true
     },
     "2": {
-      "content": "<s>",
+      "content": "[BOS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -28,7 +28,7 @@
       "special": true
     },
     "3": {
-      "content": "</s>",
+      "content": "[EOS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -36,7 +36,23 @@
       "special": true
     },
     "4": {
-      "content": "<mask>",
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -44,20 +60,24 @@
       "special": false
     }
   },
-  "bos_token": "<s>",
+  "bos_token": "[BOS]",
   "bos_token_id": 2,
   "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
+  "cls_token": "[CLS]",
+  "cls_token_id": 4,
+  "eos_token": "[EOS]",
   "eos_token_id": 3,
   "legacy": true,
-  "mask_token": "<mask>",
-  "mask_token_id": 4,
+  "mask_token": "[MASK]",
+  "mask_token_id": 6,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
+  "pad_token": "[PAD]",
   "pad_token_id": 0,
+  "sep_token": "[SEP]",
+  "sep_token_id": 5,
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "HfSentencePieceTokenizer",
-  "unk_token": "<unk>",
+  "unk_token": "[UNK]",
   "unk_token_id": 1
 }