Upload tokenizer

README.md

@@ -1,20 +1,20 @@
 ---
+language:
+- en
 license: apache-2.0
+library_name: transformers
+tags:
+- medical
+- pharmacovigilance
+- vaccines
 datasets:
 - chrisvoncsefalvay/vaers-outcomes
-language:
-- en
 metrics:
 - accuracy
 - f1
 - precision
 - recall
-library_name: transformers
 pipeline_tag: text-classification
-tags:
-- medical
-- pharmacovigilance
-- vaccines
 ---
 
 DAEDRA (Detecting Adverse Event Dispositions for Regulatory Affairs) is a pharmacovigilance language model intended to facilitate the rapid identification and extraction of high-consequence outcomes from passive pharmacovigilance reporting. It was trained on the VAERS data set, and focuses on three main outcomes:

tokenizer.json

@@ -52,15 +52,6 @@
       "rstrip": false,
       "normalized": false,
       "special": true
-    },
-    {
-      "id": 30522,
-      "content": "Pfizer",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": true,
-      "special": false
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -39,14 +39,6 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "30522": {
-      "content": "Pfizer",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
     }
   },
   "clean_up_tokenization_spaces": true,