First version of the Nasjonalbiblioteket BERT-based model

README.md

@@ -0,0 +1,34 @@
+---
+language: no
+license: CC-BY 4.0
+pipeline_tag: fill-mask
+tags:
+- norwegian
+- bert
+thumbnail: nblogo_2.png
+---
+**Release 1.0** (January 13, 2021)
+
+#NB-Bert
+
+## Description
+
+NB-Bert is a general Bert-base model built on the digital collection at the National Library of Norway.
+
+## Intended use & limitations
+
+The 1.0 version of the model is general, and should be fine-tuned for any particular use. Some fine-tuning sets may be found on Github, see
+
+* https://github.com/NBAiLab/notram
+
+## Training data
+
+The model is trained on a wide variety of text. The training set is described on
+
+* https://github.com/NBAiLab/notram
+
+## More information
+
+For more information on the model, see
+
+https://github.com/NBAiLab/notram

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "NB-BERT-base",
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "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-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "type_vocab_size": 2,
+  "vocab_size": 119547
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0467d8babd5ab2b9538d30bbd9facf67e8fcecbf1c43aac6f84a7df697ea5c5d
+size 714355318

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b37a349255374339d142b6e456afa9326015cb3c31b772a647e350a3a8108d0
+size 1083386716

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "/disk4/folder1/working/checkpoints/huggingface/native_pytorch/step1_1/", "do_basic_tokenize": true, "never_split": null}