Hugging Face's logo

DTAI-KULeuven
/
robbert-2023-dutch-base

Fill-Mask
Transformers
PyTorch
Safetensors
Dutch
roberta
Dutch
Flemish
RoBERTa
RobBERT
BERT
Inference Endpoints
5 papers
Model card Files Community
1
FremyCompany commited on
Commit
6f13c9b
•
1 Parent(s): fe03c69

Upload model

Browse files
Files changed (7) hide show
  1. config.json +33 -0
  2. merges.txt +0 -0
  3. pytorch_model.bin +3 -0
  4. special_tokens_map.json +51 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +64 -0
  7. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./olm--olm-roberta-base-dec-2022--nl--oscar.3/checkpoint-31000",
3
+ "additional_special_tokens_ids": [],
4
+ "architectures": [
5
+ "RobertaForMaskedLM"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": null,
10
+ "cls_token_id": 0,
11
+ "eos_token_id": 3,
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-05,
18
+ "mask_token_id": 4,
19
+ "max_position_embeddings": 514,
20
+ "model_type": "roberta",
21
+ "num_attention_heads": 12,
22
+ "num_hidden_layers": 12,
23
+ "pad_token_id": 1,
24
+ "position_embedding_type": "absolute",
25
+ "sep_token_id": 3,
26
+ "tokenizer_class": "RobertaTokenizerFast",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.30.2",
29
+ "type_vocab_size": 1,
30
+ "unk_token_id": 2,
31
+ "use_cache": true,
32
+ "vocab_size": 50000
33
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9fa799aee89b992ef8a493f56a3c689920ac1c3f6a11fa1e170c84a5bf28d92
3
+ size 498046571
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "clean_up_tokenization_spaces": true,
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "__type": "AddedToken",
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "errors": "replace",
29
+ "mask_token": {
30
+ "__type": "AddedToken",
31
+ "content": "<mask>",
32
+ "lstrip": true,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "model_max_length": 512,
38
+ "pad_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "sep_token": {
47
+ "__type": "AddedToken",
48
+ "content": "</s>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": {
57
+ "__type": "AddedToken",
58
+ "content": "<unk>",
59
+ "lstrip": false,
60
+ "normalized": true,
61
+ "rstrip": false,
62
+ "single_word": false
63
+ }
64
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff