Added model

README.md

@@ -0,0 +1,38 @@
+---
+language:
+- is
+- da
+- sv
+- no
+- fo
+widget:
+- text: Fina lilla<mask>, jag vill inte bliva stur.
+- text: Nu ved jeg, at du frygter<mask> og end ikke vil nægte mig din eneste søn..
+- text: Það er vorhret á<mask>, napur vindur sem hvín.
+- text: Ja, Gud signi<mask>, mítt land.
+- text: Alle dyrene i<mask> må være venner.
+tags:
+- roberta
+- icelandic
+- norwegian
+- faroese
+- danish
+- swedish
+- masked-lm
+- pytorch
+license: agpl-3.0
+---
+
+# ScandiBERT-no-faroese
+
+This is a version of the ScandiBERT model trained without any Faroese data and a different subword tokenizer.
+
+The model was trained on the data shown in the table below. Batch size was 8.8k, the model was trained for 72 epochs on 24 V100 cards for about 2 weeks.
+
+| Language  | Data                                  | Size   |
+|-----------|---------------------------------------|--------|
+| Icelandic | See IceBERT paper                     | 16 GB  |
+| Danish    | Danish Gigaword Corpus (incl Twitter) | 4,7 GB |
+| Norwegian | NCC corpus                            | 42 GB  |
+| Swedish   | Swedish Gigaword Corpus               | 3,4 GB |
+

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "./scandibert_nofo-hf/",
+  "architectures": [
+    "XLMRobertaForMaskedLM"
+  ],
+  "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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.20.1",
+  "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 sha256:2cc460411123f0b9406dee97a917352634f3afe5df92e321748e1fb42e22803b
+size 498059115

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c47e92f7b588b911aa98695b4795a0224b7bec4dd37c39bbba06b9129ac43c1
+size 1084283

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "name_or_path": "./scandibert_nofo-hf/",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}