Update README.md

README.md

@@ -76,10 +76,23 @@ model-index:
           type: vaers-outcomes
           name: vaers-outcomes
         metrics:
-          - name: accuracy
-            type: accuracy
+          - name: Accuracy, microaveraged
+            type: accuracy_microaverage
             value: 0.885
             verified: false
+          - name: F1 score, microaveraged
+            type: f1_microaverage
+            value: 0.885
+            verified: false
+          - name: Precision, macroaveraged
+            type: precision_macroaverage
+            value: 0.769
+            verified: false
+          - name: Recall, macroaveraged
+            type: recall_macroaverage
+            value: 0.688
+            verified: false
+
 ---
 
 # DAEDRA: Determining Adverse Event Disposition for Regulatory Affairs
@@ -107,7 +120,11 @@ This model is a fine-tuned version of [dmis-lab/biobert-base-cased-v1.2](https:/
 ## Model Description
 
 <!-- Provide a longer summary of what this model is/does. -->
-Some cool model...
+
+DAEDRA is a model for the identification of adverse event dispositions (outcomes) from passive pharmacovigilance data.
+The model is trained on a real-world adversomics data set spanning over three decades (1990-2023) and comprising over 1.8m records for a total corpus of 173,093,850 words constructed from a subset of reports submitted to VAERS.
+It is intended to identify, based on the narrative, whether any, or any combination, of three serious outcomes -- death, hospitalisation and ER attendance -- have occurred. 
+
 
 - **Developed by:** Chris von Csefalvay
 - **Model type:** Language model
@@ -124,7 +141,14 @@ This model was designed to facilitate the coding of passive adverse event report
 
 ## Direct Use
 
+Load the model via the `transformers` library:
+
+```
+from transformers import AutoTokenizer, AutoModel
 
+tokenizer = AutoTokenizer.from_pretrained("chrisvoncsefalvay/daedra")
+model = AutoModel.from_pretrained("chrisvoncsefalvay/daedra")
+```
 
 
 ## Out-of-Scope Use