Gerwin commited on
Commit
e1d13f4
1 Parent(s): 52dfc0b

initial commit

Browse files
Files changed (4) hide show
  1. config.json +30 -0
  2. pytorch_model.bin +3 -0
  3. tokenizer_config.json +12 -0
  4. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "C:\\Users\\KruijfGJ\\Documents\\models\\nl-en\\fp-checkpoints\\60k",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "position_embedding_type": "absolute",
26
+ "transformers_version": "4.18.0",
27
+ "type_vocab_size": 2,
28
+ "use_cache": true,
29
+ "vocab_size": 105879
30
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f611eef2fa63b8ab8dc12c9ba7acdaf6861058975ccf4ba83494c2c56c0c341a
3
+ size 672308131
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_lower_case": true,
3
+ "unk_token": "[UNK]",
4
+ "sep_token": "[SEP]",
5
+ "pad_token": "[PAD]",
6
+ "cls_token": "[CLS]",
7
+ "mask_token": "[MASK]",
8
+ "tokenize_chinese_chars": false,
9
+ "strip_accents": true,
10
+ "model_max_length": 512,
11
+ "max_len": 512
12
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff