Indonesian_1800-2000
Browse files- added_tokens.json +1 -0
- config.json +31 -0
- eval_results.txt +15 -0
- model_config.json +1 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BertForMaskedLM"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"directionality": "bidi",
|
7 |
+
"finetuning_task": "ner",
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 3072,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 512,
|
15 |
+
"model_type": "bert",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 12,
|
18 |
+
"num_labels": 20,
|
19 |
+
"output_attentions": false,
|
20 |
+
"output_hidden_states": false,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"pooler_fc_size": 768,
|
23 |
+
"pooler_num_attention_heads": 12,
|
24 |
+
"pooler_num_fc_layers": 3,
|
25 |
+
"pooler_size_per_head": 128,
|
26 |
+
"pooler_type": "first_token_transform",
|
27 |
+
"pruned_heads": {},
|
28 |
+
"torchscript": false,
|
29 |
+
"type_vocab_size": 2,
|
30 |
+
"vocab_size": 119547
|
31 |
+
}
|
eval_results.txt
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
precision recall f1-score support
|
2 |
+
|
3 |
+
DAT 0.0000 0.0000 0.0000 0
|
4 |
+
DOM 0.0000 0.0000 0.0000 0
|
5 |
+
LOC 0.2186 0.1942 0.2057 278
|
6 |
+
MISC 0.0000 0.0000 0.0000 423
|
7 |
+
ORG 0.4648 0.2095 0.2888 315
|
8 |
+
PER 0.7143 0.3933 0.5072 356
|
9 |
+
QUA 0.0000 0.0000 0.0000 0
|
10 |
+
REF 0.0000 0.0000 0.0000 0
|
11 |
+
SEP] 0.0000 0.0000 0.0000 0
|
12 |
+
|
13 |
+
micro avg 0.3190 0.1895 0.2378 1372
|
14 |
+
macro avg 0.1553 0.0886 0.1113 1372
|
15 |
+
weighted avg 0.3363 0.1895 0.2396 1372
|
model_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bert_model": "bert-base-multilingual-cased", "do_lower": false, "max_seq_length": 180, "num_labels": 20, "label_map": {"1": "O", "2": "B-PER", "3": "I-PER", "4": "B-ORG", "5": "I-ORG", "6": "B-LOC", "7": "I-LOC", "8": "B-DAT", "9": "I-DAT", "10": "B-REF", "11": "I-REF", "12": "B-DOM", "13": "I-DOM", "14": "B-QUA", "15": "I-QUA", "16": "B-MISC", "17": "I-MISC", "18": "[CLS]", "19": "[SEP]"}}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:068405383bef65839e0671a8ac461f116a74e184a2a60a588a32a800845ac081
|
3 |
+
size 711525557
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "max_len": 512, "init_inputs": []}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|