Jón Daðason commited on
Commit
9b780a1
1 Parent(s): 34d31db

Adding model

Browse files
README.md CHANGED
@@ -1,3 +1,15 @@
1
- ---
2
- license: cc-by-4.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - is
4
+ license: cc-by-4.0
5
+ datasets:
6
+ - igc
7
+ ---
8
+
9
+ # Icelandic ConvBERT-Base
10
+ This model was pretrained on the [Icelandic Gigaword Corpus](http://igc.arnastofnun.is/), which contains approximately 1.69B tokens, using default settings. The model uses a WordPiece tokenizer with a vocabulary size of 32,105.
11
+
12
+ # Acknowledgments
13
+ This research was supported with Cloud TPUs from Google's TPU Research Cloud (TRC).
14
+
15
+ This project was funded by the Language Technology Programme for Icelandic 2019-2023. The programme, which is managed and coordinated by [Almannarómur](https://almannaromur.is/), is funded by the Icelandic Ministry of Education, Science and Culture.
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ConvBertModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "conv_kernel_size": 9,
9
+ "embedding_size": 768,
10
+ "eos_token_id": 2,
11
+ "head_ratio": 2,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "convbert",
20
+ "num_attention_heads": 12,
21
+ "num_groups": 1,
22
+ "num_hidden_layers": 12,
23
+ "pad_token_id": 0,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.10.0.dev0",
26
+ "type_vocab_size": 2,
27
+ "vocab_size": 32105
28
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2700525ebe1aa1d2ebe89eead42b3d441ed3b7d27609d0c60a0a5b8735e32659
3
+ size 427696269
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 sha256:7aa466f2cad15b6ed56a7321cea6c631b1481d536c2b4ab370cddd03a8fb967e
3
+ size 427944160
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "strip_accents": false, "model_max_length": 128}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff