Leo97_KoELECTRA-small-v3-modu-ner
Leo97 · View on Hugging Face ↗
Model card
The complete upstream card, rendered from this payload's README.md — the same hash-verified bytes the torrent distributes. Images and off-site links are removed; the original card on Hugging Face carries them.
tags:
- generated_from_trainer metrics:
- precision
- recall
- f1
- accuracy model-index:
- name: KoELECTRA-small-v3-modu-ner results: [] language:
- ko pipeline_tag: token-classification widget:
- text: "서울역으로 안내해줘." example_title: "Example 1"
- text: "에어컨 온도 3도 올려줘." example_title: "Example 2"
- text: "아이유 노래 검색해줘." example_title: "Example 3"
KoELECTRA-small-v3-modu-ner
This model is a fine-tuned version of monologg/koelectra-small-v3-discriminator on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1431
- Precision: 0.8232
- Recall: 0.8449
- F1: 0.8339
- Accuracy: 0.9628
Model description
태깅 시스템 : BIO 시스템
- B-(begin) : 개체명이 시작할 때
- I-(inside) : 토큰이 개체명 중간에 있을 때
- O(outside) : 토큰이 개체명이 아닐 경우
한국정보통신기술협회(TTA) 대분류 기준을 따르는 15 가지의 태그셋
| 분류 | 표기 | 정의 |
|---|---|---|
| ARTIFACTS | AF | 사람에 의해 창조된 인공물로 문화재, 건물, 악기, 도로, 무기, 운송수단, 작품명, 공산품명이 모두 이에 해당 |
| ANIMAL | AM | 사람을 제외한 짐승 |
| CIVILIZATION | CV | 문명/문화 |
| DATE | DT | 기간 및 계절, 시기/시대 |
| EVENT | EV | 특정 사건/사고/행사 명칭 |
| STUDY_FIELD | FD | 학문 분야, 학파 및 유파 |
| LOCATION | LC | 지역/장소와 지형/지리 명칭 등을 모두 포함 |
| MATERIAL | MT | 원소 및 금속, 암석/보석, 화학물질 |
| ORGANIZATION | OG | 기관 및 단체 명칭 |
| PERSON | PS | 인명 및 인물의 별칭 (유사 인물 명칭 포함) |
| PLANT | PT | 꽃/나무, 육지식물, 해초류, 버섯류, 이끼류 |
| QUANTITY | QT | 수량/분량, 순서/순차, 수사로 이루어진 표현 |
| TIME | TI | 시계상으로 나타나는 시/시각, 시간 범위 |
| TERM | TM | 타 개체명에서 정의된 세부 개체명 이외의 개체명 |
| THEORY | TR | 특정 이론, 법칙 원리 등 |
Intended uses & limitations
How to use
You can use this model with Transformers pipeline for NER.
from transformers import AutoTokenizer, AutoModelForTokenClassification
from transformers import pipeline
tokenizer = AutoTokenizer.from_pretrained("Leo97/KoELECTRA-small-v3-modu-ner")
model = AutoModelForTokenClassification.from_pretrained("Leo97/KoELECTRA-small-v3-modu-ner")
ner = pipeline("ner", model=model, tokenizer=tokenizer)
example = "서울역으로 안내해줘."
ner_results = ner(example)
print(ner_results)
Training and evaluation data
개체명 인식(NER) 모델 학습 데이터 셋
- 문화체육관광부 > 국립국어원 > 모두의 말뭉치 > 개체명 분석 말뭉치 2021
- https://corpus.korean.go.kr/request/reausetMain.do
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 15151
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 3788 | 0.3978 | 0.5986 | 0.5471 | 0.5717 | 0.9087 |
| No log | 2.0 | 7576 | 0.2319 | 0.6986 | 0.6953 | 0.6969 | 0.9345 |
| No log | 3.0 | 11364 | 0.1838 | 0.7363 | 0.7612 | 0.7486 | 0.9444 |
| No log | 4.0 | 15152 | 0.1610 | 0.7762 | 0.7745 | 0.7754 | 0.9509 |
| No log | 5.0 | 18940 | 0.1475 | 0.7862 | 0.8011 | 0.7936 | 0.9545 |
| No log | 6.0 | 22728 | 0.1417 | 0.7857 | 0.8181 | 0.8016 | 0.9563 |
| No log | 7.0 | 26516 | 0.1366 | 0.8022 | 0.8196 | 0.8108 | 0.9584 |
| No log | 8.0 | 30304 | 0.1346 | 0.8093 | 0.8236 | 0.8164 | 0.9596 |
| No log | 9.0 | 34092 | 0.1328 | 0.8085 | 0.8299 | 0.8190 | 0.9602 |
| No log | 10.0 | 37880 | 0.1332 | 0.8110 | 0.8368 | 0.8237 | 0.9608 |
| No log | 11.0 | 41668 | 0.1323 | 0.8157 | 0.8347 | 0.8251 | 0.9612 |
| No log | 12.0 | 45456 | 0.1353 | 0.8118 | 0.8402 | 0.8258 | 0.9611 |
| No log | 13.0 | 49244 | 0.1370 | 0.8152 | 0.8416 | 0.8282 | 0.9616 |
| No log | 14.0 | 53032 | 0.1368 | 0.8164 | 0.8415 | 0.8287 | 0.9616 |
| No log | 15.0 | 56820 | 0.1378 | 0.8187 | 0.8438 | 0.8310 | 0.9621 |
| No log | 16.0 | 60608 | 0.1389 | 0.8217 | 0.8438 | 0.8326 | 0.9626 |
| No log | 17.0 | 64396 | 0.1380 | 0.8266 | 0.8426 | 0.8345 | 0.9631 |
| No log | 18.0 | 68184 | 0.1428 | 0.8216 | 0.8445 | 0.8329 | 0.9625 |
| No log | 19.0 | 71972 | 0.1431 | 0.8232 | 0.8455 | 0.8342 | 0.9628 |
| 0.1712 | 20.0 | 75760 | 0.1431 | 0.8232 | 0.8449 | 0.8339 | 0.9628 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
Magnet link
Opens the swarm directly in your torrent client — no file download needed. Copy-paste works too:
magnet:?xt=urn:btih:bffe836b10f04057eba8a84ad3a7702fe76e0911&dn=Leo97_KoELECTRA-small-v3-modu-nerOpen magnet in torrent client · infohash bffe836b10f04057eba8a84ad3a7702fe76e0911
Files & hashes
| Path | Size | sha1 | sha256 |
|---|---|---|---|
| README.md | 5.5 KB (5,589 B) | 0dabb2e3520c89f00549c3628a8a543609668633 | e9101a415628260a581a4eac7c5e6a2fa52aa390b78f713fab1f5bb44caf8391 |
| config.json | 1.8 KB (1,880 B) | 03cf74ee8bdc5d1a871ba727b1506b96151402c9 | 433b9d9d6272e0820a62062b13be5d631891d5a509ecb8ae9c782cccfe740a78 |
| model.safetensors | 53.7 MB (56,284,578 B) | 99eb32df914fe6883526a1098c7903057639b3e3 | c7613112988b28df5db3a98e3317521d0eaeeb2e173144e1bd061b2d50286c48 |
| pytorch_model.bin | 53.7 MB (56,330,037 B) | 4c064375cd88667f3be1855ce025738be46bbc2d | 6d572aed6fa7e3a5dea23bdef206e109a1b7314b9ae7b5238cbc684d84f22d34 |
| runs/Apr03_02-10-29_9f8a0a3a5bbf/1680487868.0161226/events.out.tfevents.1680487868.9f8a0a3a5bbf.543.1 | 5.7 KB (5,872 B) | ee80c6d7515fd868b31b72cbaaa695c5e2edba08 | 5aa5fa210fccbea33f05d434a070949b16ba42694a5d5ba4a6f3de0fddf8a3f0 |
| runs/Apr03_02-10-29_9f8a0a3a5bbf/events.out.tfevents.1680487868.9f8a0a3a5bbf.543.0 | 10.5 KB (10,754 B) | 6bf951853499870de5c87d52b7e4879d864f9c05 | 9aebe2540054182a599ca28ed5c0618be45595e68b2de4d9bee9bf5c8571fa08 |
| runs/Apr05_03-30-38_5b47c4ecdbee/1680665525.2874877/events.out.tfevents.1680665525.5b47c4ecdbee.452.1 | 5.7 KB (5,872 B) | bbe596e672a8bbfd5816d5a5ca432efa7991bce4 | c99bab261610568a83c917de5c045d55efcef814c70ff69eb47b15ab6f76f4a8 |
| runs/Apr05_03-30-38_5b47c4ecdbee/events.out.tfevents.1680665525.5b47c4ecdbee.452.0 | 7.0 KB (7,180 B) | 2d699878a1fb5a408583f12ea6f6f5c13c036f95 | 6e3f2c806537f33cab2b2407dd3e53ac0bfb179f75b7eb5f970972eccad38fe1 |
| runs/Apr05_05-16-04_010a653d2914/1680671809.7113647/events.out.tfevents.1680671809.010a653d2914.146.1 | 5.7 KB (5,872 B) | 10c120220e17e8d0b3bc183415216509ac8b773e | 8a97443e4c3af5718ad92b32dd8335f2fd8591da36d2e7fefe7988ff500acda6 |
| runs/Apr05_05-16-04_010a653d2914/events.out.tfevents.1680671809.010a653d2914.146.0 | 8.0 KB (8,142 B) | b716f7e5d5de1a7eeaef9d84036cedec84c8e179 | 64a04465030461df143477db6366429d6b5dfa045f667a6ad8fd6e111af683eb |
| runs/Apr07_03-09-05_adf6afa1096d/1680837002.4824874/events.out.tfevents.1680837002.adf6afa1096d.4586.1 | 5.7 KB (5,872 B) | b47c7f3de99fdc959d28cf02162ed5cf8725591a | 40cfbea78f576f5e394d24a062ce3dd91062f4c50261688c856792904686f760 |
| runs/Apr07_03-09-05_adf6afa1096d/events.out.tfevents.1680837002.adf6afa1096d.4586.0 | 15.2 KB (15,565 B) | 0c1ebb52243870cd1be995976c46e1bb21b934f4 | e982294771be10a503ad0c1f57dfd85ff3a2f9381647ad25c9cf72ed8ed2327a |
| runs/Mar29_05-40-00_f57d0dd35d0a/1680068508.4352155/events.out.tfevents.1680068508.f57d0dd35d0a.195.1 | 5.7 KB (5,824 B) | adc40a31c95a4993ca34b1e41a174982c5f74b91 | 211af70f5fbfe5bba4d846dad0114f335b20f7d727086f510c4fe121474e5e40 |
| runs/Mar29_05-40-00_f57d0dd35d0a/events.out.tfevents.1680068508.f57d0dd35d0a.195.0 | 10.5 KB (10,706 B) | cb52e4a84fd66b6aee1e72e5a838aaa9531457b8 | 96de636e7e75df10a7146fd5ceb01ebe458856c6e55fa898818d22e027c9e7b0 |
| runs/Mar31_08-59-31_efb60e2b93ff/1680253186.4787786/events.out.tfevents.1680253186.efb60e2b93ff.189.1 | 6.0 KB (6,116 B) | 04dda1adc363d3188c6ab60ae974781afec71f6d | bd4562c4558b0410fb23d07cf94fe541330cf935e78d8d011f29ee1290734465 |
| runs/Mar31_08-59-31_efb60e2b93ff/events.out.tfevents.1680253186.efb60e2b93ff.189.0 | 5.9 KB (6,052 B) | 30523c050afd667f7dcd0abff64768897746ad16 | db19cd103b257a69153cad0532d59486e78231f3a63499410571ef2e047fa34a |
| runs/Mar31_09-24-05_efb60e2b93ff/1680254654.5058205/events.out.tfevents.1680254654.efb60e2b93ff.189.3 | 5.7 KB (5,872 B) | 0669d7676ede3ea246fbe4463c7a06cbb4c92f02 | ed63abc0500474d8e6b1acd3f5a65eedd56123312ad4e72cd34f5b39153ca569 |
| runs/Mar31_09-24-05_efb60e2b93ff/events.out.tfevents.1680254654.efb60e2b93ff.189.2 | 6.0 KB (6,121 B) | b06b2f994c51ba94ea11577cca77d0002ff588de | eec3d271965d9733856e89f91aff83d6d7c8cbbbd149f96946523783e44fbcca |
| special_tokens_map.json | 125 B (125 B) | a8b3208c2884c4efb86e49300fdd3dc877220cdf | b6d346be366a7d1d48332dbc9fdf3bf8960b5d879522b7799ddba59e76237ee3 |
| tokenizer.json | 795.8 KB (814,850 B) | 62536f1d69029ade4f4c1da8126151b3ceafda8c | d5c7a9a8996aca4fee55a3664381b012bd7dbb3e190061b2591c02502b7171b6 |
| tokenizer_config.json | 365 B (365 B) | 8c121819598835167f3f45db6cf762c24fb6551d | 4ba179ceb2f3ec5c263ba31328f80abb779d1c2bcbba716697c871fbecb44b84 |
| training_args.bin | 3.6 KB (3,643 B) | 8449cbec74faa6100cec18981238ad79bfce0ed9 | 56828df94887494d132b96d11de558121bbee7817db9257304be070483f3c522 |
| vocab.txt | 257.2 KB (263,327 B) | 6033c2fd2b9266df1abb47ebe2704163eebbc4d7 | 6e886927dfcecd22029b1ba80c10a1374740259c1067fc3a28d964b7ae2d55a7 |
Cite this release
- Canonical URL
- https://aiseedbank.org/models/Leo97_KoELECTRA-small-v3-modu-ner/
- Slug
- Leo97_KoELECTRA-small-v3-modu-ner
- Infohash
- bffe836b10f04057eba8a84ad3a7702fe76e0911
- License
- no license recorded
- Signing key fingerprint
- 85a3b32c3712427b
Every file carries a locally computed sha256 — verify a download against the signed sums: Leo97_KoELECTRA-small-v3-modu-ner.SHA256SUMS (+ minisign signature).
Provenance
| Upstream repository | Leo97/KoELECTRA-small-v3-modu-ner |
|---|---|
| Revision (pinned) | bb9d562674e260712d9779f140ff5564a9e44d36 |
| Fetched at | 2026-09-03T17:46:39Z |
| License at fetch | no license recorded |
| Snapshot tool | huggingface · seedbank 0.1.0 |
Trackers
- udp://announce.aitorrent.org:6969/announce
- http://announce.aitorrent.org:7070/announce
- udp://announce2.aitorrent.org:6970/announce
- http://announce2.aitorrent.org:7071/announce
- udp://tracker.opentrackr.org:1337/announce
- udp://open.demonii.com:1337/announce
- udp://open.stealth.si:80/announce
- udp://exodus.desync.com:6969/announce
- udp://tracker.torrent.eu.org:451/announce
✓ verified · rehash-vs-hf-metadata at 2026-09-03T17:46:43Z
no license recorded108.5 MB (113,810,214 bytes)transformerspytorchtensorboardsafetensorselectratoken-classificationgenerated_from_trainerendpoints_compatible1 language (ko)