StevenLimcorn commited on
Commit
5b9a389
1 Parent(s): 9904650

initial commit; fine-tuned on BaPOS

Browse files
config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "indonesian-roberta-base-bapos-tagger",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10",
25
+ "11": "LABEL_11",
26
+ "12": "LABEL_12",
27
+ "13": "LABEL_13",
28
+ "14": "LABEL_14",
29
+ "15": "LABEL_15",
30
+ "16": "LABEL_16",
31
+ "17": "LABEL_17",
32
+ "18": "LABEL_18",
33
+ "19": "LABEL_19",
34
+ "20": "LABEL_20",
35
+ "21": "LABEL_21",
36
+ "22": "LABEL_22",
37
+ "23": "LABEL_23",
38
+ "24": "LABEL_24",
39
+ "25": "LABEL_25",
40
+ "26": "LABEL_26",
41
+ "27": "LABEL_27",
42
+ "28": "LABEL_28",
43
+ "29": "LABEL_29",
44
+ "30": "LABEL_30",
45
+ "31": "LABEL_31",
46
+ "32": "LABEL_32",
47
+ "33": "LABEL_33",
48
+ "34": "LABEL_34",
49
+ "35": "LABEL_35",
50
+ "36": "LABEL_36",
51
+ "37": "LABEL_37",
52
+ "38": "LABEL_38",
53
+ "39": "LABEL_39",
54
+ "40": "LABEL_40"
55
+ },
56
+ "initializer_range": 0.02,
57
+ "intermediate_size": 3072,
58
+ "label2id": {
59
+ "LABEL_0": 0,
60
+ "LABEL_1": 1,
61
+ "LABEL_10": 10,
62
+ "LABEL_11": 11,
63
+ "LABEL_12": 12,
64
+ "LABEL_13": 13,
65
+ "LABEL_14": 14,
66
+ "LABEL_15": 15,
67
+ "LABEL_16": 16,
68
+ "LABEL_17": 17,
69
+ "LABEL_18": 18,
70
+ "LABEL_19": 19,
71
+ "LABEL_2": 2,
72
+ "LABEL_20": 20,
73
+ "LABEL_21": 21,
74
+ "LABEL_22": 22,
75
+ "LABEL_23": 23,
76
+ "LABEL_24": 24,
77
+ "LABEL_25": 25,
78
+ "LABEL_26": 26,
79
+ "LABEL_27": 27,
80
+ "LABEL_28": 28,
81
+ "LABEL_29": 29,
82
+ "LABEL_3": 3,
83
+ "LABEL_30": 30,
84
+ "LABEL_31": 31,
85
+ "LABEL_32": 32,
86
+ "LABEL_33": 33,
87
+ "LABEL_34": 34,
88
+ "LABEL_35": 35,
89
+ "LABEL_36": 36,
90
+ "LABEL_37": 37,
91
+ "LABEL_38": 38,
92
+ "LABEL_39": 39,
93
+ "LABEL_4": 4,
94
+ "LABEL_40": 40,
95
+ "LABEL_5": 5,
96
+ "LABEL_6": 6,
97
+ "LABEL_7": 7,
98
+ "LABEL_8": 8,
99
+ "LABEL_9": 9
100
+ },
101
+ "layer_norm_eps": 1e-05,
102
+ "max_position_embeddings": 514,
103
+ "model_type": "roberta",
104
+ "num_attention_heads": 12,
105
+ "num_hidden_layers": 12,
106
+ "pad_token_id": 1,
107
+ "position_embedding_type": "absolute",
108
+ "torch_dtype": "float32",
109
+ "transformers_version": "4.8.2",
110
+ "type_vocab_size": 1,
111
+ "use_cache": true,
112
+ "vocab_size": 50265
113
+ }
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 sha256:9500fc965752002dcaea6d148ea0f1537855e960ee31500afb349e7103be76dc
3
+ size 496430961
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ca24b4718e4a50e28d2005aa494b58512fa2c235f920a07daacceed7c0a8bc2
3
+ size 496634000
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": true, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "name_or_path": "flax-community/indonesian-roberta-base", "tokenizer_class": "RobertaTokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff