Text Classification
Transformers
Safetensors
Korean
bert
klue
korean
minwon
complaint
public-administration
text-embeddings-inference
Instructions to use atti433/minde-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use atti433/minde-classifier with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="atti433/minde-classifier")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("atti433/minde-classifier") model = AutoModelForSequenceClassification.from_pretrained("atti433/minde-classifier", device_map="auto") - Notebooks
- Google Colab
- Kaggle
v10-relabel: LLM 재라벨링 + stratified 7:1.5:1.5 재분할, macro F1 0.896
Browse files- config.json +8 -5
- model.safetensors +1 -1
- tokenizer_config.json +7 -119
- training_args.bin +2 -2
config.json
CHANGED
|
@@ -1,10 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
"architectures": [
|
| 4 |
"BertForSequenceClassification"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
|
| 7 |
"classifier_dropout": null,
|
|
|
|
|
|
|
| 8 |
"hidden_act": "gelu",
|
| 9 |
"hidden_dropout_prob": 0.1,
|
| 10 |
"hidden_size": 768,
|
|
@@ -23,6 +26,7 @@
|
|
| 23 |
},
|
| 24 |
"initializer_range": 0.02,
|
| 25 |
"intermediate_size": 3072,
|
|
|
|
| 26 |
"label2id": {
|
| 27 |
"\uac74\ucd95": 1,
|
| 28 |
"\uacbd\uc81c": 10,
|
|
@@ -42,11 +46,10 @@
|
|
| 42 |
"num_attention_heads": 12,
|
| 43 |
"num_hidden_layers": 12,
|
| 44 |
"pad_token_id": 0,
|
| 45 |
-
"position_embedding_type": "absolute",
|
| 46 |
"problem_type": "single_label_classification",
|
| 47 |
-
"
|
| 48 |
-
"transformers_version": "
|
| 49 |
"type_vocab_size": 2,
|
| 50 |
-
"use_cache":
|
| 51 |
"vocab_size": 32009
|
| 52 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
"architectures": [
|
| 4 |
"BertForSequenceClassification"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": null,
|
| 11 |
"hidden_act": "gelu",
|
| 12 |
"hidden_dropout_prob": 0.1,
|
| 13 |
"hidden_size": 768,
|
|
|
|
| 26 |
},
|
| 27 |
"initializer_range": 0.02,
|
| 28 |
"intermediate_size": 3072,
|
| 29 |
+
"is_decoder": false,
|
| 30 |
"label2id": {
|
| 31 |
"\uac74\ucd95": 1,
|
| 32 |
"\uacbd\uc81c": 10,
|
|
|
|
| 46 |
"num_attention_heads": 12,
|
| 47 |
"num_hidden_layers": 12,
|
| 48 |
"pad_token_id": 0,
|
|
|
|
| 49 |
"problem_type": "single_label_classification",
|
| 50 |
+
"tie_word_embeddings": true,
|
| 51 |
+
"transformers_version": "5.12.1",
|
| 52 |
"type_vocab_size": 2,
|
| 53 |
+
"use_cache": false,
|
| 54 |
"vocab_size": 32009
|
| 55 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 442554396
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4605e0f05ce8bc39fc603e51ac6408b8efcbb07192ff4c62881da54bcd07de51
|
| 3 |
size 442554396
|
tokenizer_config.json
CHANGED
|
@@ -1,119 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 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 |
-
"32000": {
|
| 44 |
-
"content": "[ADDR]",
|
| 45 |
-
"lstrip": false,
|
| 46 |
-
"normalized": false,
|
| 47 |
-
"rstrip": false,
|
| 48 |
-
"single_word": false,
|
| 49 |
-
"special": true
|
| 50 |
-
},
|
| 51 |
-
"32001": {
|
| 52 |
-
"content": "[NAME]",
|
| 53 |
-
"lstrip": false,
|
| 54 |
-
"normalized": false,
|
| 55 |
-
"rstrip": false,
|
| 56 |
-
"single_word": false,
|
| 57 |
-
"special": true
|
| 58 |
-
},
|
| 59 |
-
"32002": {
|
| 60 |
-
"content": "[ORG]",
|
| 61 |
-
"lstrip": false,
|
| 62 |
-
"normalized": false,
|
| 63 |
-
"rstrip": false,
|
| 64 |
-
"single_word": false,
|
| 65 |
-
"special": true
|
| 66 |
-
},
|
| 67 |
-
"32003": {
|
| 68 |
-
"content": "[NUM]",
|
| 69 |
-
"lstrip": false,
|
| 70 |
-
"normalized": false,
|
| 71 |
-
"rstrip": false,
|
| 72 |
-
"single_word": false,
|
| 73 |
-
"special": true
|
| 74 |
-
},
|
| 75 |
-
"32004": {
|
| 76 |
-
"content": "[TEL]",
|
| 77 |
-
"lstrip": false,
|
| 78 |
-
"normalized": false,
|
| 79 |
-
"rstrip": false,
|
| 80 |
-
"single_word": false,
|
| 81 |
-
"special": true
|
| 82 |
-
},
|
| 83 |
-
"32005": {
|
| 84 |
-
"content": "[ACCT]",
|
| 85 |
-
"lstrip": false,
|
| 86 |
-
"normalized": false,
|
| 87 |
-
"rstrip": false,
|
| 88 |
-
"single_word": false,
|
| 89 |
-
"special": true
|
| 90 |
-
},
|
| 91 |
-
"32006": {
|
| 92 |
-
"content": "[BIZ]",
|
| 93 |
-
"lstrip": false,
|
| 94 |
-
"normalized": false,
|
| 95 |
-
"rstrip": false,
|
| 96 |
-
"single_word": false,
|
| 97 |
-
"special": true
|
| 98 |
-
},
|
| 99 |
-
"32007": {
|
| 100 |
-
"content": "[LOC]",
|
| 101 |
-
"lstrip": false,
|
| 102 |
-
"normalized": false,
|
| 103 |
-
"rstrip": false,
|
| 104 |
-
"single_word": false,
|
| 105 |
-
"special": true
|
| 106 |
-
},
|
| 107 |
-
"32008": {
|
| 108 |
-
"content": "[PERSON]",
|
| 109 |
-
"lstrip": false,
|
| 110 |
-
"normalized": false,
|
| 111 |
-
"rstrip": false,
|
| 112 |
-
"single_word": false,
|
| 113 |
-
"special": true
|
| 114 |
-
}
|
| 115 |
-
},
|
| 116 |
-
"additional_special_tokens": [
|
| 117 |
"[ADDR]",
|
| 118 |
"[NAME]",
|
| 119 |
"[ORG]",
|
|
@@ -124,10 +14,8 @@
|
|
| 124 |
"[LOC]",
|
| 125 |
"[PERSON]"
|
| 126 |
],
|
| 127 |
-
"
|
| 128 |
-
"
|
| 129 |
-
"do_basic_tokenize": true,
|
| 130 |
-
"do_lower_case": false,
|
| 131 |
"mask_token": "[MASK]",
|
| 132 |
"model_max_length": 512,
|
| 133 |
"never_split": null,
|
|
|
|
| 1 |
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_basic_tokenize": true,
|
| 5 |
+
"do_lower_case": false,
|
| 6 |
+
"extra_special_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
"[ADDR]",
|
| 8 |
"[NAME]",
|
| 9 |
"[ORG]",
|
|
|
|
| 14 |
"[LOC]",
|
| 15 |
"[PERSON]"
|
| 16 |
],
|
| 17 |
+
"is_local": false,
|
| 18 |
+
"local_files_only": false,
|
|
|
|
|
|
|
| 19 |
"mask_token": "[MASK]",
|
| 20 |
"model_max_length": 512,
|
| 21 |
"never_split": null,
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2e387dd0f005f266c5dfe046fbe16fe2495ab09efcd66d4085762e6b7def63a
|
| 3 |
+
size 4832
|