versae commited on
Commit
83e1255
1 Parent(s): b7c249e

First version of the Nasjonalbiblioteket BERT-based model

Browse files
README.md ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: no
3
+ license: CC-BY 4.0
4
+ pipeline_tag: fill-mask
5
+ tags:
6
+ - norwegian
7
+ - bert
8
+ thumbnail: nblogo_2.png
9
+ ---
10
+ **Release 1.0** (January 13, 2021)
11
+
12
+ #NB-Bert
13
+
14
+ ## Description
15
+
16
+ NB-Bert is a general Bert-base model built on the digital collection at the National Library of Norway.
17
+
18
+ ## Intended use & limitations
19
+
20
+ 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
21
+
22
+ * https://github.com/NBAiLab/notram
23
+
24
+ ## Training data
25
+
26
+ The model is trained on a wide variety of text. The training set is described on
27
+
28
+ * https://github.com/NBAiLab/notram
29
+
30
+ ## More information
31
+
32
+ For more information on the model, see
33
+
34
+ https://github.com/NBAiLab/notram
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "NB-BERT-base",
3
+ "attention_probs_dropout_prob": 0.1,
4
+ "directionality": "bidi",
5
+ "gradient_checkpointing": false,
6
+ "hidden_act": "gelu",
7
+ "hidden_dropout_prob": 0.1,
8
+ "hidden_size": 768,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 3072,
11
+ "layer_norm_eps": 1e-12,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "bert",
14
+ "num_attention_heads": 12,
15
+ "num_hidden_layers": 12,
16
+ "pad_token_id": 0,
17
+ "pooler_fc_size": 768,
18
+ "pooler_num_attention_heads": 12,
19
+ "pooler_num_fc_layers": 3,
20
+ "pooler_size_per_head": 128,
21
+ "pooler_type": "first_token_transform",
22
+ "position_embedding_type": "absolute",
23
+ "type_vocab_size": 2,
24
+ "vocab_size": 119547
25
+ }
nblogo_2.png ADDED
Binary file (3.08 kB). View file
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0467d8babd5ab2b9538d30bbd9facf67e8fcecbf1c43aac6f84a7df697ea5c5d
3
+ size 714355318
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b37a349255374339d142b6e456afa9326015cb3c31b772a647e350a3a8108d0
3
+ size 1083386716
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
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}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff