Added model

.gitattributes

@@ -0,0 +1,3 @@
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+training_args.bin filter=lfs diff=lfs merge=lfs -text
+sentencepiece.bpe.model filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,66 @@
+{
+  "_name_or_path": "vesteinn/ScandiBERT",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+   "0": "O",
+    "1": "B-Date",
+    "2": "B-Location",
+    "3": "B-Miscellaneous",
+    "4": "B-Money",
+    "5": "B-Organization",
+    "6": "B-Percent",
+    "7": "B-Person",
+    "8": "B-Time",
+    "9": "I-Date",
+    "10": "I-Location",
+    "11": "I-Miscellaneous",
+    "12": "I-Money",
+    "13": "I-Organization",
+    "14": "I-Percent",
+    "15": "I-Person",
+    "16": "I-Time"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+   "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50005
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca6c9151533dcbe7dbafa5dee632acd51b207d6a557dd6d76f978f619fb1b3f3
+size 495558449

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fca70379c621cffc6910d3988182faedd75c5b01a8adcb552405a8f83ce7a41
+size 1084241

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "special_tokens_map_file": null, "name_or_path": "vesteinn/ScandiBERT", "sp_model_kwargs": {}, "add_prefix_space": true, "tokenizer_class": "XLMRobertaTokenizer"}