louisbrulenaudet/lemone-router-l

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-large. It achieves the following results on the evaluation set:

• Loss: 0.4734
• Accuracy: 0.9191

Usage

# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained("louisbrulenaudet/lemone-router-l")
model = AutoModelForSequenceClassification.from_pretrained("louisbrulenaudet/lemone-router-l")

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2.6763799752474963e-05
• train_batch_size: 4
• eval_batch_size: 64
• seed: 25
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6402	1.0	11233	0.6569	0.8630
0.5031	2.0	22466	0.5058	0.9025
0.2196	3.0	33699	0.4734	0.9191

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-l}},
}

Feedback

If you have any feedback, please reach out at [email protected].