Muhammad Ridzki Nugraha commited on
Commit
7ca9600
·
verified ·
1 Parent(s): 14d3ef4

Upload folder using huggingface_hub

Browse files
indobert-base/config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 5,
3
+ "add_cross_attention": false,
4
+ "architectures": [
5
+ "BertForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "bos_token_id": null,
9
+ "classifier_dropout": null,
10
+ "decoder_start_token_id": null,
11
+ "directionality": "bidi",
12
+ "dtype": "float32",
13
+ "eos_token_id": null,
14
+ "finetuning_task": null,
15
+ "hidden_act": "gelu",
16
+ "hidden_dropout_prob": 0.1,
17
+ "hidden_size": 768,
18
+ "id2label": {
19
+ "0": "LABEL_0",
20
+ "1": "LABEL_1",
21
+ "2": "LABEL_2",
22
+ "3": "LABEL_3"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
26
+ "is_decoder": false,
27
+ "label2id": {
28
+ "LABEL_0": 0,
29
+ "LABEL_1": 1,
30
+ "LABEL_2": 2,
31
+ "LABEL_3": 3
32
+ },
33
+ "layer_norm_eps": 1e-12,
34
+ "max_position_embeddings": 512,
35
+ "model_type": "bert",
36
+ "num_attention_heads": 12,
37
+ "num_hidden_layers": 12,
38
+ "output_past": true,
39
+ "pad_token_id": 0,
40
+ "pooler_fc_size": 768,
41
+ "pooler_num_attention_heads": 12,
42
+ "pooler_num_fc_layers": 3,
43
+ "pooler_size_per_head": 128,
44
+ "pooler_type": "first_token_transform",
45
+ "prefix": null,
46
+ "pruned_heads": {},
47
+ "task_specific_params": null,
48
+ "tie_word_embeddings": true,
49
+ "torchscript": false,
50
+ "transformers_version": "5.2.0",
51
+ "type_vocab_size": 2,
52
+ "use_bfloat16": false,
53
+ "use_cache": true,
54
+ "vocab_size": 50000
55
+ }
indobert-base/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8d1200476cabe2292657ee03024e55ae13c2192c490658fb892dd02f4a0de43
3
+ size 497801200
indobert-base/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
indobert-base/tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "is_local": false,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "BertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }