SetFit with sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 as the Sentence Transformer embedding model. A LogisticRegression instance is used for classification.
The model has been trained using an efficient few-shot learning technique that involves:
- Fine-tuning a Sentence Transformer with contrastive learning.
- Training a classification head with features from the fine-tuned Sentence Transformer.
Model Details
Model Description
- Model Type: SetFit
- Sentence Transformer body: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
- Classification head: a LogisticRegression instance
- Maximum Sequence Length: 128 tokens
- Number of Classes: 36 classes
Model Sources
- Repository: SetFit on GitHub
- Paper: Efficient Few-Shot Learning Without Prompts
- Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts
Model Labels
Label | Examples |
---|---|
[단말기]모바일 U+Shop |
|
[콜봇공통]장애처리 |
|
[콜봇상담]IPTV장애 |
|
[콜봇상담]결합상품문의 |
|
[콜봇상담]기기변경문의 |
|
[콜봇상담]납부방법변경 |
|
[콜봇상담]납부확인서 발급 |
|
[콜봇상담]듀얼넘버 문의 |
|
[콜봇상담]모바일 부가서비스 가입 및 해지 |
|
[콜봇상담]선택약정할인상태 안내 및 등록기능 |
|
[콜봇상담]세금계산서발행 |
|
[콜봇상담]스팸차단 서비스 신청 및 해지 |
|
[콜봇상담]약정문의(공통) |
|
[콜봇상담]연체문의(공통) |
|
[콜봇상담]요금납부 |
|
[콜봇상담]요금문의(공통) |
|
[콜봇상담]요금제변경 |
|
[콜봇상담]유심 구매 및 이동 문의 |
|
[콜봇상담]이전설치 |
|
[콜봇상담]인터넷 해지 |
|
[콜봇상담]인터넷장애 |
|
[콜봇상담]일반상담(공통) |
|
[콜봇상담]일시정지 및 일시정지 해제(공통) |
|
[콜봇상담]일시정지 및 일시정지 해제(모) |
|
[콜봇상담]청구요금조회 |
|
[콜봇상담]통화연결음 가입 및 해지 |
|
[콜봇상담]통화중대기 가입 및 해지 |
|
[콜봇상담]해지(공통) |
|
[콜봇상담]홈서비스 가입 |
|
[콜봇상담]환불_이중납부 |
|
[콜봇상담]휴대폰 분실문의 |
|
[콜봇상담]휴대폰결제 한도변경 |
|
[콜봇상담]휴대폰결제(공통) |
|
[콜봇상담]휴대폰보험문의및보상신청 |
|
[콜봇이벤트]로밍상담 재질의 |
|
[프리미어요금제약정할인]프리미어 요금제 약정할인 |
|
Uses
Direct Use for Inference
First install the SetFit library:
pip install setfit
Then you can load this model and run inference.
from setfit import SetFitModel
# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("huiyeong/setfit-callbot-text")
# Run inference
preds = model("분실")
Training Details
Training Set Metrics
Training set | Min | Median | Max |
---|---|---|---|
Word count | 1 | 3.1483 | 27 |
Label | Training Sample Count |
---|---|
[단말기]모바일 U+Shop | 50 |
[콜봇공통]장애처리 | 50 |
[콜봇상담]IPTV장애 | 50 |
[콜봇상담]결합상품문의 | 50 |
[콜봇상담]기기변경문의 | 50 |
[콜봇상담]납부방법변경 | 50 |
[콜봇상담]납부확인서 발급 | 50 |
[콜봇상담]듀얼넘버 문의 | 50 |
[콜봇상담]모바일 부가서비스 가입 및 해지 | 50 |
[콜봇상담]선택약정할인상태 안내 및 등록기능 | 50 |
[콜봇상담]세금계산서발행 | 50 |
[콜봇상담]스팸차단 서비스 신청 및 해지 | 50 |
[콜봇상담]약정문의(공통) | 50 |
[콜봇상담]연체문의(공통) | 50 |
[콜봇상담]요금납부 | 50 |
[콜봇상담]요금문의(공통) | 50 |
[콜봇상담]요금제변경 | 50 |
[콜봇상담]유심 구매 및 이동 문의 | 50 |
[콜봇상담]이전설치 | 50 |
[콜봇상담]인터넷 해지 | 50 |
[콜봇상담]인터넷장애 | 50 |
[콜봇상담]일반상담(공통) | 50 |
[콜봇상담]일시정지 및 일시정지 해제(공통) | 50 |
[콜봇상담]일시정지 및 일시정지 해제(모) | 50 |
[콜봇상담]청구요금조회 | 50 |
[콜봇상담]통화연결음 가입 및 해지 | 50 |
[콜봇상담]통화중대기 가입 및 해지 | 50 |
[콜봇상담]해지(공통) | 50 |
[콜봇상담]홈서비스 가입 | 50 |
[콜봇상담]환불_이중납부 | 50 |
[콜봇상담]휴대폰 분실문의 | 50 |
[콜봇상담]휴대폰결제 한도변경 | 50 |
[콜봇상담]휴대폰결제(공통) | 50 |
[콜봇상담]휴대폰보험문의및보상신청 | 50 |
[콜봇이벤트]로밍상담 재질의 | 50 |
[프리미어요금제약정할인]프리미어 요금제 약정할인 | 50 |
Training Hyperparameters
- batch_size: (16, 16)
- num_epochs: (5, 5)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 5
- body_learning_rate: (2e-05, 1e-05)
- head_learning_rate: 0.01
- loss: CosineSimilarityLoss
- distance_metric: cosine_distance
- margin: 0.25
- end_to_end: False
- use_amp: False
- warmup_proportion: 0.1
- l2_weight: 0.01
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: False
Training Results
Epoch | Step | Training Loss | Validation Loss |
---|---|---|---|
0.0009 | 1 | 0.1825 | - |
0.0444 | 50 | 0.2286 | - |
0.0889 | 100 | 0.1987 | - |
0.1333 | 150 | 0.1976 | - |
0.1778 | 200 | 0.1674 | - |
0.2222 | 250 | 0.1477 | - |
0.2667 | 300 | 0.1317 | - |
0.3111 | 350 | 0.1235 | - |
0.3556 | 400 | 0.0987 | - |
0.4 | 450 | 0.0872 | - |
0.4444 | 500 | 0.09 | - |
0.4889 | 550 | 0.0701 | - |
0.5333 | 600 | 0.0751 | - |
0.5778 | 650 | 0.0674 | - |
0.6222 | 700 | 0.062 | - |
0.6667 | 750 | 0.0556 | - |
0.7111 | 800 | 0.0473 | - |
0.7556 | 850 | 0.0574 | - |
0.8 | 900 | 0.0504 | - |
0.8444 | 950 | 0.0477 | - |
0.8889 | 1000 | 0.0398 | - |
0.9333 | 1050 | 0.0414 | - |
0.9778 | 1100 | 0.0385 | - |
1.0222 | 1150 | 0.0368 | - |
1.0667 | 1200 | 0.0417 | - |
1.1111 | 1250 | 0.0329 | - |
1.1556 | 1300 | 0.0284 | - |
1.2 | 1350 | 0.0232 | - |
1.2444 | 1400 | 0.0291 | - |
1.2889 | 1450 | 0.0229 | - |
1.3333 | 1500 | 0.0319 | - |
1.3778 | 1550 | 0.024 | - |
1.4222 | 1600 | 0.0204 | - |
1.4667 | 1650 | 0.02 | - |
1.5111 | 1700 | 0.0179 | - |
1.5556 | 1750 | 0.0189 | - |
1.6 | 1800 | 0.0202 | - |
1.6444 | 1850 | 0.0149 | - |
1.6889 | 1900 | 0.0173 | - |
1.7333 | 1950 | 0.0168 | - |
1.7778 | 2000 | 0.0187 | - |
1.8222 | 2050 | 0.0144 | - |
1.8667 | 2100 | 0.0172 | - |
1.9111 | 2150 | 0.0147 | - |
1.9556 | 2200 | 0.0154 | - |
2.0 | 2250 | 0.0167 | - |
2.0444 | 2300 | 0.0131 | - |
2.0889 | 2350 | 0.0125 | - |
2.1333 | 2400 | 0.0081 | - |
2.1778 | 2450 | 0.01 | - |
2.2222 | 2500 | 0.0116 | - |
2.2667 | 2550 | 0.0119 | - |
2.3111 | 2600 | 0.0105 | - |
2.3556 | 2650 | 0.0115 | - |
2.4 | 2700 | 0.0125 | - |
2.4444 | 2750 | 0.0117 | - |
2.4889 | 2800 | 0.0068 | - |
2.5333 | 2850 | 0.0119 | - |
2.5778 | 2900 | 0.0088 | - |
2.6222 | 2950 | 0.013 | - |
2.6667 | 3000 | 0.0114 | - |
2.7111 | 3050 | 0.0094 | - |
2.7556 | 3100 | 0.0082 | - |
2.8 | 3150 | 0.0122 | - |
2.8444 | 3200 | 0.0089 | - |
2.8889 | 3250 | 0.0058 | - |
2.9333 | 3300 | 0.0083 | - |
2.9778 | 3350 | 0.0059 | - |
3.0222 | 3400 | 0.0059 | - |
3.0667 | 3450 | 0.0086 | - |
3.1111 | 3500 | 0.0059 | - |
3.1556 | 3550 | 0.0067 | - |
3.2 | 3600 | 0.0062 | - |
3.2444 | 3650 | 0.0109 | - |
3.2889 | 3700 | 0.0067 | - |
3.3333 | 3750 | 0.0064 | - |
3.3778 | 3800 | 0.0067 | - |
3.4222 | 3850 | 0.0083 | - |
3.4667 | 3900 | 0.0051 | - |
3.5111 | 3950 | 0.0075 | - |
3.5556 | 4000 | 0.0038 | - |
3.6 | 4050 | 0.0056 | - |
3.6444 | 4100 | 0.0047 | - |
3.6889 | 4150 | 0.0049 | - |
3.7333 | 4200 | 0.0038 | - |
3.7778 | 4250 | 0.0081 | - |
3.8222 | 4300 | 0.004 | - |
3.8667 | 4350 | 0.0071 | - |
3.9111 | 4400 | 0.0083 | - |
3.9556 | 4450 | 0.0035 | - |
4.0 | 4500 | 0.0067 | - |
4.0444 | 4550 | 0.0073 | - |
4.0889 | 4600 | 0.0055 | - |
4.1333 | 4650 | 0.0062 | - |
4.1778 | 4700 | 0.0041 | - |
4.2222 | 4750 | 0.0065 | - |
4.2667 | 4800 | 0.0044 | - |
4.3111 | 4850 | 0.0053 | - |
4.3556 | 4900 | 0.0049 | - |
4.4 | 4950 | 0.0055 | - |
4.4444 | 5000 | 0.0043 | - |
4.4889 | 5050 | 0.0059 | - |
4.5333 | 5100 | 0.0045 | - |
4.5778 | 5150 | 0.0033 | - |
4.6222 | 5200 | 0.0048 | - |
4.6667 | 5250 | 0.0045 | - |
4.7111 | 5300 | 0.0046 | - |
4.7556 | 5350 | 0.0065 | - |
4.8 | 5400 | 0.005 | - |
4.8444 | 5450 | 0.004 | - |
4.8889 | 5500 | 0.0039 | - |
4.9333 | 5550 | 0.0045 | - |
4.9778 | 5600 | 0.0051 | - |
Framework Versions
- Python: 3.11.13
- SetFit: 1.1.2
- Sentence Transformers: 4.1.0
- Transformers: 4.52.4
- PyTorch: 2.6.0+cu124
- Datasets: 3.6.0
- Tokenizers: 0.21.1
Citation
BibTeX
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
- Downloads last month
- 0
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support