Upload tokenizer

special_tokens_map.json

@@ -1,27 +1,15 @@
 {
-  "bos_token": "<s>",
+  "bos_token": "[CLS]",
   "cls_token": "[CLS]",
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": "[MASK]",
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
+  "eos_token": "[SEP]",
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
+  "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "unk_token": "[UNK]"
 }

spiece.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5cbdfa8aa7c54c8c5af85b78c309c54a5f2749a20468bf6f60eee007fe6fec1
-size 805634
+oid sha256:a7f87f538d8c73fb0a6a34efb7ba6e3488f920341119c02c208bce7965cf248e
+size 810161

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<unk>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "<s>",
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,22 +17,6 @@
       "special": true
     },
     "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "3": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "4": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -40,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "5": {
+    "3": {
       "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
@@ -48,28 +32,27 @@
       "single_word": false,
       "special": true
     },
-    "6": {
+    "4": {
       "content": "[MASK]",
-      "lstrip": false,
-      "normalized": false,
+      "lstrip": true,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "additional_special_tokens": [],
-  "bos_token": "<s>",
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": true,
-  "eos_token": "</s>",
-  "extra_ids": 0,
-  "legacy": true,
+  "eos_token": "[SEP]",
+  "keep_accents": true,
   "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
+  "remove_space": true,
   "sep_token": "[SEP]",
   "sp_model_kwargs": {},
-  "tokenizer_class": "T5Tokenizer",
-  "unk_token": "<unk>"
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "[UNK]"
 }