tokenizer

added_tokens.json

@@ -1,8 +1,8 @@
 {
-  "<authors>": 250006,
-  "<country>": 250003,
-  "<intervention>": 250005,
-  "<participants>": 250002,
-  "<period>": 250004,
-  "not reported": 250007
+  "<authors>": 31094,
+  "<country>": 31091,
+  "<intervention>": 31093,
+  "<participants>": 31090,
+  "<period>": 31092,
+  "not reported": 31095
 }

special_tokens_map.json

@@ -1,48 +1,34 @@
 {
-  "bos_token": {
-    "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": "</s>",
+    "content": "[CLS]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
+    "content": "[MASK]",
+    "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<pad>",
+    "content": "[PAD]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "sep_token": {
-    "content": "</s>",
+    "content": "[SEP]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
-    "content": "<unk>",
+    "content": "[UNK]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7d7b8c1064277e3c44de7598db9b63db516025c48dd25de90e821334b242849
-size 17083862
+oid sha256:b61e49e3cf301d8a1658e985881567507a9dae5c91023ed422dc79c247444bba
+size 718205

tokenizer_config.json

@@ -1,46 +1,46 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<pad>",
+    "101": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "102": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<unk>",
+    "103": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "250001": {
-      "content": "<mask>",
-      "lstrip": true,
+    "104": {
+      "content": "[MASK]",
+      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "250002": {
+    "31090": {
       "content": "<participants>",
       "lstrip": false,
       "normalized": true,
@@ -48,7 +48,7 @@
       "single_word": false,
       "special": false
     },
-    "250003": {
+    "31091": {
       "content": "<country>",
       "lstrip": false,
       "normalized": true,
@@ -56,7 +56,7 @@
       "single_word": false,
       "special": false
     },
-    "250004": {
+    "31092": {
       "content": "<period>",
       "lstrip": false,
       "normalized": true,
@@ -64,7 +64,7 @@
       "single_word": false,
       "special": false
     },
-    "250005": {
+    "31093": {
       "content": "<intervention>",
       "lstrip": false,
       "normalized": true,
@@ -72,7 +72,7 @@
       "single_word": false,
       "special": false
     },
-    "250006": {
+    "31094": {
       "content": "<authors>",
       "lstrip": false,
       "normalized": true,
@@ -80,7 +80,7 @@
       "single_word": false,
       "special": false
     },
-    "250007": {
+    "31095": {
       "content": "not reported",
       "lstrip": false,
       "normalized": true,
@@ -89,15 +89,18 @@
       "special": false
     }
   },
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
   "extra_special_tokens": {},
-  "mask_token": "<mask>",
+  "mask_token": "[MASK]",
   "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "XLMRobertaTokenizer",
-  "unk_token": "<unk>"
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }