mrzaizai2k/model_routing_voice

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:

1. Fine-tuning a Sentence Transformer with contrastive learning.
2. 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: 5 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
1	'Đèn cảnh báo này có nghĩa là gì' '이 기능은 어떻게 작동하나요' 'How do I pair my phone with the car'
3	'Tăng âm lượng lên' 'Turn up the volume' 'Play some music'
4	'Check for software updates' 'データをクラウドにアップロードして' '設定をクラウドと同期して'
0	'Open the trunk for me' 'Mở cốp xe giúp tôi' '차 문을 열어 주세요'
2	'一番近いガソリンスタンドを探して' '自宅まで案内してください' 'Find the nearest gas station'

Evaluation

Metrics

Label	Accuracy
all	1.0

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("mrzaizai2k/model_routing_voice")
# Run inference
preds = model("音楽を再生してください")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	1	4.0811	9

Label	Training Sample Count
0	7
1	8
2	7
3	8
4	7

Training Hyperparameters

• batch_size: (8, 8)
• num_epochs: (4, 4)
• max_steps: -1
• sampling_strategy: oversampling
• 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
• seed: 42
• eval_max_steps: -1
• load_best_model_at_end: True

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0073	1	0.4469	-
0.3650	50	0.064	-
0.7299	100	0.0107	-
1.0	137	-	0.0224
1.0949	150	0.0037	-
1.4599	200	0.0012	-
1.8248	250	0.0007	-
2.0	274	-	0.0225
2.1898	300	0.0007	-
2.5547	350	0.0007	-
2.9197	400	0.0005	-
3.0	411	-	0.0236
3.2847	450	0.0004	-
3.6496	500	0.0007	-
4.0	548	-	0.0241

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.10.19
• SetFit: 1.0.3
• Sentence Transformers: 5.2.3
• Transformers: 4.41.2
• PyTorch: 2.10.0+cu128
• Datasets: 2.19.0
• Tokenizers: 0.19.1

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}
}