versae commited on
Commit
359e05b
1 Parent(s): ca8a4aa

First version of nb-bert-large (codename: T10)

Browse files
Files changed (5) hide show
  1. config.json +20 -0
  2. pytorch_model.bin +3 -0
  3. tf_model.h5 +3 -0
  4. tokenizer_config.json +1 -0
  5. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_probs_dropout_prob": 0.1,
3
+ "gradient_checkpointing": false,
4
+ "hidden_act": "gelu",
5
+ "hidden_dropout_prob": 0.1,
6
+ "hidden_size": 1024,
7
+ "initializer_range": 0.02,
8
+ "intermediate_size": 4096,
9
+ "layer_norm_eps": 1e-12,
10
+ "max_position_embeddings": 512,
11
+ "model_type": "bert",
12
+ "num_attention_heads": 16,
13
+ "num_hidden_layers": 24,
14
+ "pad_token_id": 0,
15
+ "position_embedding_type": "absolute",
16
+ "transformers_version": "4.3.3",
17
+ "type_vocab_size": 2,
18
+ "use_cache": true,
19
+ "vocab_size": 50000
20
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de1b3793557797b9bc0955911a86c49bcbedb8ddffffa4435800bcc77844fc81
3
+ size 1424927978
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d363ba0219810916f3f62e7731bc7da486c3b68bd0a5d0ee5f56595178e7ba78
3
+ size 1630090424
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "special_tokens_map_file": null, "name_or_path": "/disk4/folder1/working/checkpoints/huggingface/T5_noTram2_BERT_norwegian_uncased/native_pytorch/", "do_basic_tokenize": true, "never_split": null}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff