Update

README.md

@@ -13,7 +13,7 @@ metrics:
 - f1
 ---
 
-# Ælæctra - Finetuned for Named Entity Recognition on the [DaNE dataset](https://danlp.alexandra.dk/304bd159d5de/datasets/ddt.zip) (Hvingelby et al., 2020).
+# Ælæctra - Finetuned for Named Entity Recognition on the [DaNE dataset](https://danlp.alexandra.dk/304bd159d5de/datasets/ddt.zip) (Hvingelby et al., 2020) by Malte Højmark-Bertelsen.
 **Ælæctra** is a Danish Transformer-based language model created to enhance the variety of Danish NLP resources with a more efficient model compared to previous state-of-the-art (SOTA) models.
 
 Ælæctra was pretrained with the ELECTRA-Small (Clark et al., 2020) pretraining approach by using the Danish Gigaword Corpus (Strømberg-Derczynski et al., 2020) and evaluated on Named Entity Recognition (NER) tasks. Since NER only presents a limited picture of Ælæctra's capabilities I am very interested in further evaluations. Therefore, if you employ it for any task, feel free to hit me up your findings!

config.json

@@ -9,30 +9,30 @@
   "hidden_dropout_prob": 0.1,
   "hidden_size": 256,
   "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2",
-    "3": "LABEL_3",
-    "4": "LABEL_4",
-    "5": "LABEL_5",
-    "6": "LABEL_6",
-    "7": "LABEL_7",
-    "8": "LABEL_8",
-    "9": "LABEL_9"
+    "0": "B-PER",
+    "1": "I-PER",
+    "2": "B-LOC",
+    "3": "I-LOC",
+    "4": "B-ORG",
+    "5": "I-ORG",
+    "6": "O",
+    "7": "[PAD]",
+    "8": "[CLS]",
+    "9": "[SEP]"
   },
   "initializer_range": 0.02,
   "intermediate_size": 1024,
   "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2,
-    "LABEL_3": 3,
-    "LABEL_4": 4,
-    "LABEL_5": 5,
-    "LABEL_6": 6,
-    "LABEL_7": 7,
-    "LABEL_8": 8,
-    "LABEL_9": 9
+    "B-PER": 0,
+    "I-PER": 1,
+    "B-LOC": 2,
+    "I-LOC": 3,
+    "B-ORG": 4,
+    "I-ORG": 5,
+    "O": 6,
+    "[PAD]": 7,
+    "[CLS]": 8,
+    "[SEP]": 9
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,