tokenizer

added_tokens.json

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

special_tokens_map.json

@@ -1,34 +1,48 @@
 {
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "cls_token": {
-    "content": "[CLS]",
+    "content": "<s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "mask_token": {
-    "content": "[MASK]",
+  "eos_token": {
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "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": "[SEP]",
+    "content": "</s>",
     "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:b61e49e3cf301d8a1658e985881567507a9dae5c91023ed422dc79c247444bba
-size 718205
+oid sha256:9ce0dfc5d3962904c8e89549f410f07fe0ac8309107860a092e636dd5a2111d6
+size 17084180

tokenizer_config.json

@@ -1,46 +1,46 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
-      "content": "[UNK]",
+    "1": {
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[CLS]",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[SEP]",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "104": {
-      "content": "[MASK]",
-      "lstrip": false,
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "31090": {
+    "250002": {
       "content": "<participants>",
       "lstrip": false,
       "normalized": true,
@@ -48,7 +48,7 @@
       "single_word": false,
       "special": false
     },
-    "31091": {
+    "250003": {
       "content": "<country>",
       "lstrip": false,
       "normalized": true,
@@ -56,7 +56,7 @@
       "single_word": false,
       "special": false
     },
-    "31092": {
+    "250004": {
       "content": "<period>",
       "lstrip": false,
       "normalized": true,
@@ -64,7 +64,7 @@
       "single_word": false,
       "special": false
     },
-    "31093": {
+    "250005": {
       "content": "<intervention>",
       "lstrip": false,
       "normalized": true,
@@ -72,7 +72,7 @@
       "single_word": false,
       "special": false
     },
-    "31094": {
+    "250006": {
       "content": "<authors>",
       "lstrip": false,
       "normalized": true,
@@ -80,7 +80,7 @@
       "single_word": false,
       "special": false
     },
-    "31095": {
+    "250007": {
       "content": "not reported",
       "lstrip": false,
       "normalized": true,
@@ -89,18 +89,16 @@
       "special": false
     }
   },
-  "clean_up_tokenization_spaces": false,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
   "extra_special_tokens": {},
-  "mask_token": "[MASK]",
+  "mask_token": "<mask>",
   "model_max_length": 512,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
 }