Lemone-Router: A Series of Fine-Tuned Classification Models for French Taxation
Lemone-router is a series of classification models designed to produce an optimal multi-agent system for different branches of tax law. Trained on a base of 49k lines comprising a set of synthetic questions generated by GPT-4 Turbo and Llama 3.1 70B, which have been further refined through evol-instruction tuning and manual curation and authority documents, these models are based on an 8-category decomposition of the classification scheme derived from the Bulletin officiel des finances publiques - impôts :
label2id = {
"Bénéfices professionnels": 0,
"Contrôle et contentieux": 1,
"Dispositifs transversaux": 2,
"Fiscalité des entreprises": 3,
"Patrimoine et enregistrement": 4,
"Revenus particuliers": 5,
"Revenus patrimoniaux": 6,
"Taxes sur la consommation": 7
}
id2label = {
0: "Bénéfices professionnels",
1: "Contrôle et contentieux",
2: "Dispositifs transversaux",
3: "Fiscalité des entreprises",
4: "Patrimoine et enregistrement",
5: "Revenus particuliers",
6: "Revenus patrimoniaux",
7: "Taxes sur la consommation"
}
This model is a fine-tuned version of intfloat/multilingual-e5-base. It achieves the following results on the evaluation set of 5000 texts:
- Loss: 0.4096
- Accuracy: 0.9265
Usage
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("louisbrulenaudet/lemone-router-m")
model = AutoModelForSequenceClassification.from_pretrained("louisbrulenaudet/lemone-router-m")
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 4.099463734610582e-05
- train_batch_size: 16
- eval_batch_size: 64
- seed: 23
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.5371 | 1.0 | 2809 | 0.4147 | 0.8680 |
0.3154 | 2.0 | 5618 | 0.3470 | 0.8914 |
0.2241 | 3.0 | 8427 | 0.3345 | 0.9147 |
0.1273 | 4.0 | 11236 | 0.3788 | 0.9187 |
0.0525 | 5.0 | 14045 | 0.4096 | 0.9265 |
Training Hardware
- On Cloud: No
- GPU Model: 1 x NVIDIA H100 NVL
- CPU Model: AMD EPYC 9V84 96-Core Processor
Framework versions
- Transformers 4.45.2
- Pytorch 2.4.1+cu121
- Datasets 2.21.0
- Tokenizers 0.20.1
Citation
If you use this code in your research, please use the following BibTeX entry.
@misc{louisbrulenaudet2024,
author = {Louis Brulé Naudet},
title = {Lemone-Router: A Series of Fine-Tuned Classification Models for French Taxation},
year = {2024}
howpublished = {\url{https://huggingface.co/datasets/louisbrulenaudet/lemone-router-m}},
}
Feedback
If you have any feedback, please reach out at [email protected].
- Downloads last month
- 38
Model tree for louisbrulenaudet/lemone-router-m
Base model
intfloat/multilingual-e5-base