Hugging Face's logo

ilos-vigil
/
bigbird-small-indonesian

Fill-Mask
Transformers
PyTorch
TensorBoard
Safetensors
Indonesian
big_bird
Inference Endpoints
Model card Files Metrics Community
1
ilos-vigil commited on
Commit
7f12618
•
1 Parent(s): 82481db

Upload model and tokenizer

Browse files

Unfinished model training at ~1.0 epoch/6450 steps

Files changed (5) hide show
  1. config.json +31 -0
  2. pytorch_model.bin +3 -0
  3. special_tokens_map.json +51 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +63 -0
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BigBirdForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "attention_type": "block_sparse",
7
+ "block_size": 64,
8
+ "bos_token_id": 1,
9
+ "classifier_dropout": null,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu_new",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 512,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 2048,
16
+ "layer_norm_eps": 1e-12,
17
+ "max_position_embeddings": 4096,
18
+ "model_type": "big_bird",
19
+ "num_attention_heads": 8,
20
+ "num_hidden_layers": 4,
21
+ "num_random_blocks": 3,
22
+ "pad_token_id": 0,
23
+ "rescale_embeddings": false,
24
+ "sep_token_id": 66,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.23.1",
27
+ "type_vocab_size": 2,
28
+ "use_bias": true,
29
+ "use_cache": true,
30
+ "vocab_size": 30000
31
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46402790e3f9dbff379efccf0bb1e26ae1eb9bb4a64dd3bd8832cfdce428fe5b
3
+ size 122558078
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": "[CLS]",
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": "[SEP]",
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 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "</s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "cls_token": {
11
+ "__type": "AddedToken",
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "__type": "AddedToken",
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "mask_token": {
27
+ "__type": "AddedToken",
28
+ "content": "[MASK]",
29
+ "lstrip": true,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "model_max_length": 4096,
35
+ "name_or_path": "google/bigbird-roberta-base",
36
+ "pad_token": {
37
+ "__type": "AddedToken",
38
+ "content": "<pad>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "sep_token": {
45
+ "__type": "AddedToken",
46
+ "content": "[SEP]",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ "sp_model_kwargs": {},
53
+ "special_tokens_map_file": "/home/user/.cache/huggingface/hub/models--google--bigbird-roberta-base/snapshots/5a145f7852cba9bd431386a58137bf8a29903b90/special_tokens_map.json",
54
+ "tokenizer_class": "BigBirdTokenizer",
55
+ "unk_token": {
56
+ "__type": "AddedToken",
57
+ "content": "<unk>",
58
+ "lstrip": false,
59
+ "normalized": true,
60
+ "rstrip": false,
61
+ "single_word": false
62
+ }
63
+ }