Text Classification
Transformers
Safetensors
Indonesian
bert
indobert
intent-classification
text-embeddings-inference
Instructions to use Firdania/sindesa-indobert-intent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Firdania/sindesa-indobert-intent with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Firdania/sindesa-indobert-intent")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Firdania/sindesa-indobert-intent") model = AutoModelForSequenceClassification.from_pretrained("Firdania/sindesa-indobert-intent", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload 8 files
Browse files- config.json +58 -0
- metrics_indobert.json +147 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_num_labels": 5,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"directionality": "bidi",
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "oos",
|
| 15 |
+
"1": "tanya_durasi",
|
| 16 |
+
"2": "tanya_informasi",
|
| 17 |
+
"3": "tanya_jadwal",
|
| 18 |
+
"4": "tanya_kendala",
|
| 19 |
+
"5": "tanya_lokasi",
|
| 20 |
+
"6": "tanya_pembaruan",
|
| 21 |
+
"7": "tanya_pembayaran",
|
| 22 |
+
"8": "tanya_prosedur",
|
| 23 |
+
"9": "tanya_status",
|
| 24 |
+
"10": "tanya_syarat"
|
| 25 |
+
},
|
| 26 |
+
"initializer_range": 0.02,
|
| 27 |
+
"intermediate_size": 3072,
|
| 28 |
+
"label2id": {
|
| 29 |
+
"oos": 0,
|
| 30 |
+
"tanya_durasi": 1,
|
| 31 |
+
"tanya_informasi": 2,
|
| 32 |
+
"tanya_jadwal": 3,
|
| 33 |
+
"tanya_kendala": 4,
|
| 34 |
+
"tanya_lokasi": 5,
|
| 35 |
+
"tanya_pembaruan": 6,
|
| 36 |
+
"tanya_pembayaran": 7,
|
| 37 |
+
"tanya_prosedur": 8,
|
| 38 |
+
"tanya_status": 9,
|
| 39 |
+
"tanya_syarat": 10
|
| 40 |
+
},
|
| 41 |
+
"layer_norm_eps": 1e-12,
|
| 42 |
+
"max_position_embeddings": 512,
|
| 43 |
+
"model_type": "bert",
|
| 44 |
+
"num_attention_heads": 12,
|
| 45 |
+
"num_hidden_layers": 12,
|
| 46 |
+
"output_past": true,
|
| 47 |
+
"pad_token_id": 0,
|
| 48 |
+
"pooler_fc_size": 768,
|
| 49 |
+
"pooler_num_attention_heads": 12,
|
| 50 |
+
"pooler_num_fc_layers": 3,
|
| 51 |
+
"pooler_size_per_head": 128,
|
| 52 |
+
"pooler_type": "first_token_transform",
|
| 53 |
+
"position_embedding_type": "absolute",
|
| 54 |
+
"transformers_version": "4.57.6",
|
| 55 |
+
"type_vocab_size": 2,
|
| 56 |
+
"use_cache": true,
|
| 57 |
+
"vocab_size": 50000
|
| 58 |
+
}
|
metrics_indobert.json
ADDED
|
@@ -0,0 +1,147 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"validation": {
|
| 3 |
+
"accuracy": 0.8556034482758621,
|
| 4 |
+
"macro_f1": 0.886913586129003,
|
| 5 |
+
"weighted_f1": 0.8557812935961824
|
| 6 |
+
},
|
| 7 |
+
"test": {
|
| 8 |
+
"accuracy": 0.83632447954056,
|
| 9 |
+
"macro_f1": 0.8634187089939357,
|
| 10 |
+
"weighted_f1": 0.8365568925411568
|
| 11 |
+
},
|
| 12 |
+
"challenge": {
|
| 13 |
+
"accuracy": 0.83,
|
| 14 |
+
"macro_f1": 0.8078033078033078,
|
| 15 |
+
"weighted_f1": 0.8078033078033077
|
| 16 |
+
},
|
| 17 |
+
"test_per_intent": {
|
| 18 |
+
"tanya_prosedur": {
|
| 19 |
+
"precision": 0.7672727272727272,
|
| 20 |
+
"recall": 0.7814814814814814,
|
| 21 |
+
"f1-score": 0.7743119266055046,
|
| 22 |
+
"support": 270.0
|
| 23 |
+
},
|
| 24 |
+
"tanya_kendala": {
|
| 25 |
+
"precision": 0.7875,
|
| 26 |
+
"recall": 0.7682926829268293,
|
| 27 |
+
"f1-score": 0.7777777777777778,
|
| 28 |
+
"support": 164.0
|
| 29 |
+
},
|
| 30 |
+
"tanya_informasi": {
|
| 31 |
+
"precision": 0.8271604938271605,
|
| 32 |
+
"recall": 0.8007968127490039,
|
| 33 |
+
"f1-score": 0.8137651821862348,
|
| 34 |
+
"support": 251.0
|
| 35 |
+
},
|
| 36 |
+
"tanya_status": {
|
| 37 |
+
"precision": 0.7606837606837606,
|
| 38 |
+
"recall": 0.8811881188118812,
|
| 39 |
+
"f1-score": 0.8165137614678899,
|
| 40 |
+
"support": 101.0
|
| 41 |
+
},
|
| 42 |
+
"tanya_lokasi": {
|
| 43 |
+
"precision": 0.875,
|
| 44 |
+
"recall": 0.8,
|
| 45 |
+
"f1-score": 0.835820895522388,
|
| 46 |
+
"support": 35.0
|
| 47 |
+
},
|
| 48 |
+
"tanya_pembaruan": {
|
| 49 |
+
"precision": 0.8523489932885906,
|
| 50 |
+
"recall": 0.8819444444444444,
|
| 51 |
+
"f1-score": 0.8668941979522184,
|
| 52 |
+
"support": 144.0
|
| 53 |
+
},
|
| 54 |
+
"tanya_pembayaran": {
|
| 55 |
+
"precision": 0.8625,
|
| 56 |
+
"recall": 0.8734177215189873,
|
| 57 |
+
"f1-score": 0.8679245283018868,
|
| 58 |
+
"support": 79.0
|
| 59 |
+
},
|
| 60 |
+
"tanya_syarat": {
|
| 61 |
+
"precision": 0.9183673469387755,
|
| 62 |
+
"recall": 0.8653846153846154,
|
| 63 |
+
"f1-score": 0.8910891089108911,
|
| 64 |
+
"support": 208.0
|
| 65 |
+
},
|
| 66 |
+
"tanya_jadwal": {
|
| 67 |
+
"precision": 0.9523809523809523,
|
| 68 |
+
"recall": 0.9090909090909091,
|
| 69 |
+
"f1-score": 0.9302325581395349,
|
| 70 |
+
"support": 44.0
|
| 71 |
+
},
|
| 72 |
+
"tanya_durasi": {
|
| 73 |
+
"precision": 0.9322033898305084,
|
| 74 |
+
"recall": 0.9649122807017544,
|
| 75 |
+
"f1-score": 0.9482758620689655,
|
| 76 |
+
"support": 57.0
|
| 77 |
+
},
|
| 78 |
+
"oos": {
|
| 79 |
+
"precision": 0.975,
|
| 80 |
+
"recall": 0.975,
|
| 81 |
+
"f1-score": 0.975,
|
| 82 |
+
"support": 40.0
|
| 83 |
+
}
|
| 84 |
+
},
|
| 85 |
+
"challenge_per_intent": {
|
| 86 |
+
"tanya_jadwal": {
|
| 87 |
+
"precision": 1.0,
|
| 88 |
+
"recall": 0.1,
|
| 89 |
+
"f1-score": 0.18181818181818182,
|
| 90 |
+
"support": 10.0
|
| 91 |
+
},
|
| 92 |
+
"tanya_status": {
|
| 93 |
+
"precision": 1.0,
|
| 94 |
+
"recall": 0.4,
|
| 95 |
+
"f1-score": 0.5714285714285714,
|
| 96 |
+
"support": 10.0
|
| 97 |
+
},
|
| 98 |
+
"tanya_informasi": {
|
| 99 |
+
"precision": 0.5,
|
| 100 |
+
"recall": 1.0,
|
| 101 |
+
"f1-score": 0.6666666666666666,
|
| 102 |
+
"support": 10.0
|
| 103 |
+
},
|
| 104 |
+
"tanya_prosedur": {
|
| 105 |
+
"precision": 0.625,
|
| 106 |
+
"recall": 1.0,
|
| 107 |
+
"f1-score": 0.7692307692307693,
|
| 108 |
+
"support": 10.0
|
| 109 |
+
},
|
| 110 |
+
"tanya_pembaruan": {
|
| 111 |
+
"precision": 1.0,
|
| 112 |
+
"recall": 0.8,
|
| 113 |
+
"f1-score": 0.8888888888888888,
|
| 114 |
+
"support": 10.0
|
| 115 |
+
},
|
| 116 |
+
"tanya_kendala": {
|
| 117 |
+
"precision": 1.0,
|
| 118 |
+
"recall": 1.0,
|
| 119 |
+
"f1-score": 1.0,
|
| 120 |
+
"support": 10.0
|
| 121 |
+
},
|
| 122 |
+
"tanya_lokasi": {
|
| 123 |
+
"precision": 1.0,
|
| 124 |
+
"recall": 1.0,
|
| 125 |
+
"f1-score": 1.0,
|
| 126 |
+
"support": 10.0
|
| 127 |
+
},
|
| 128 |
+
"tanya_durasi": {
|
| 129 |
+
"precision": 1.0,
|
| 130 |
+
"recall": 1.0,
|
| 131 |
+
"f1-score": 1.0,
|
| 132 |
+
"support": 10.0
|
| 133 |
+
},
|
| 134 |
+
"tanya_pembayaran": {
|
| 135 |
+
"precision": 1.0,
|
| 136 |
+
"recall": 1.0,
|
| 137 |
+
"f1-score": 1.0,
|
| 138 |
+
"support": 10.0
|
| 139 |
+
},
|
| 140 |
+
"tanya_syarat": {
|
| 141 |
+
"precision": 1.0,
|
| 142 |
+
"recall": 1.0,
|
| 143 |
+
"f1-score": 1.0,
|
| 144 |
+
"support": 10.0
|
| 145 |
+
}
|
| 146 |
+
}
|
| 147 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd8338f7ad1d343ed4c697a8cac68754bae869ecefaacc869bb44ac2c8d48eb0
|
| 3 |
+
size 497822756
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"never_split": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca9259f59296e7b812cbef61dd4385033ed99a9683cbd01e91aec3142f9b9050
|
| 3 |
+
size 5905
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|