This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/all-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/all-MiniLM-L12-v2
Classification head: a LogisticRegression instance
Maximum Sequence Length: 128 tokens
Number of Classes: 48 classes

Model Sources

Repository: SetFit on GitHub
Paper: Efficient Few-Shot Learning Without Prompts
Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts

Evaluation

Metrics

Label	Accuracy
all	0.8776

Uses

Direct Use for Inference

First install the SetFit library:

pip install setfit

Then you can load this model and run inference.

python

from setfit import SetFitModel

# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("setfit_model_id")
# Run inference
preds = model("Food and Bons Drinks included")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	2	6.5514	23

Label	Training Sample Count
Housing / rent	3
Housing / house loan	14
Housing / utilities & bills	17
Housing / services & maintenance	1
Housing / other	1
Food & Drinks / groceries	0
Food & Drinks / eating out	1
Food & Drinks / other	10
Leisure & Entertainment / sports & hobbies	2
Leisure & Entertainment / culture & events	1
Leisure & Entertainment / travel	1
Leisure & Entertainment / other	51
Transportation / car loan & leasing	13
Transportation / fuel	10
Transportation / public transportation	3
Transportation / taxi & carpool	5
Transportation / maitenance	22
Transportation / other	158
Recurrent Payments / loans	9
Recurrent Payments / insurance	28
Recurrent Payments / subscription	10
Recurrent Payments / other	2
Investment / securities	1
Investment / retirement & savings	0
Investment / real estate	5
Investment / other	4
Shopping / clothing	8
Shopping / electronics & multimedia	2
Shopping / sporting goods	24
Shopping / housing equipment	2
Shopping / other	21
Healthy & Beauty / doctor fees	13
Healthy & Beauty / pharmacy	9
Healthy & Beauty / beauty & self-care	5
Healthy & Beauty / veterinary	4
Healthy & Beauty / other	8
Bank services / transfers	2
Bank services / withdrawal	3
Bank services / general fees	1
Bank services / other	2
Other / taxes	0
Other / kids	6
Other / pets	5
Other / other	12

Training Hyperparameters

batch_size: (32, 32)
num_epochs: (1, 1)
max_steps: -1
sampling_strategy: oversampling
num_iterations: 10
body_learning_rate: (2e-05, 2e-05)
head_learning_rate: 2e-05
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
0.0027	1	0.1199	-
0.1370	50	0.0613	-
0.2740	100	0.0247	-
0.4110	150	0.0174	-
0.5479	200	0.0125	-
0.6849	250	0.011	-
0.8219	300	0.0143	-
0.9589	350	0.0127	-

Framework Versions

Python: 3.12.6
SetFit: 1.1.2
Sentence Transformers: 3.3.1
Transformers: 4.46.3
PyTorch: 2.5.1+cpu
Datasets: 3.5.0
Tokenizers: 0.20.3

Citation

BibTeX

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}
}

yassine123Z/EmissionFactor-mapper2-v2

SetFit with sentence-transformers/all-MiniLM-L12-v2