---
base_model:
- deepseek-ai/DeepSeek-R1-Distill-Llama-8B

tags:
- text-classification
- brazilian-portuguese
- nfe
pipeline_tag: text-classification
library_name: transformers
license: apache-2.0
---

# deepseek-r1-distill-llama-8B-finetuned-nfe-detection-r1-distill-llama-8B-finetuned-nfe-detection

> **Finetuned DeepSeek R1 Distill Llama 8B for detecting suppliers under federal sanctions (CGU/CEIS) in Brazilian NF‑e documents.**

[![Hugging Face](https://img.shields.io/badge/HF-Model-informational?logo=huggingface)](https://huggingface.co/CleitonOERocha/deepseek-r1-distill-llama-8B-finetuned-nfe-detection)
[![License: Apache‑2.0](https://img.shields.io/badge/License-Apache%202.0-green)](LICENSE)

---

## TL;DR

* **Task**  Binary text classification (`0` = ordinary purchase, `1` = purchase from sanctioned supplier)
* **Base model**  `deepseek-ai/DeepSeek-R1-Distill-Llama-8B` (8 B params)
* **Training data**  40 000 NF‑e records (70 % train, 30 % test)
* **Best epoch**  5 / 5 (early‑stopping on validation loss)
* **Performance**  Accuracy 0.952 | F1 0.953 | ROC‑AUC 0.981
* **License**  Apache 2.0 (weights, code & dataset)

---

## Motivation

Brazil’s federal administration issued **1.76 M invoices in 2023**. Detecting suppliers already punished by regulators is tedious and error‑prone. This model automates the first triage step, highlighting suspicious transactions for auditors.

The work is part of master’s dissertation *Detection of Potentially Untrustworthy Companies through Government Procurement Extracts* (UFBA, 2025).

---

## Quick start

```python
from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline

model_name = "CleitonOERocha/deepseek-r1-distill-llama-8B-finetuned-nfe-detection"

model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=2)
tokenizer = AutoTokenizer.from_pretrained(model_name)

clf = pipeline(
    "text-classification",
    model=model,
    tokenizer=tokenizer,
    top_k=None,
    device="cuda"   # "cpu" also works
)

print(clf("[CLS] Destinatario: XXX BATALHAO LOG [SEP] Municipio emitente: SÃO PAULO [SEP] Descricao do produto: MICROFONE LAPELA BY-M1 PRETO P2 [SEP] Qtd: 2 [SEP] Total: 649.78"))

```

Example output:

```json

[{"label": "LABEL_1", "score": 0.9752885699272156}, {"label": "LABEL_0", "score": 0.024711500853300095}]

```

---

### Dataset creation

- Crawled NF‑e ZIPs from [Portal da Transparência](https://www.portaltransparencia.gov.br/)
- Merged with sanction list from CGU/CEIS
- Filtering → deduplication → text normalisation → label propagation

---

## Model details

| Item                | Value                               |
| ------------------- | ----------------------------------- |
| Base                | DeepSeek R1 Distill Llama 8B        |
| Parameters          | 8 B                                 |
| Architecture        | Decoder‑only Transformer            |
| Max sequence length | 4 096                               |
| Fine‑tuned epochs   | 5                                   |
| Learning rate       | 2 × 10⁻⁵                            |
| Optimizer           | AdamW                               |
| Loss                | Cross‑entropy                       |

> Dataset: **40 000** NF‑e lines (28 000 train | 12 000 test)

### Evaluation metrics

| Metric    | Value |
| --------- | ----- |
| Accuracy  | **0.9519** |
| Precision | 0.9457 |
| Recall    | 0.9599 |
| F1‑score  | **0.9527** |
| ROC‑AUC   | 0.9812 |

### Confusion matrix (test set)

|          | Pred 0 | Pred 1 |
|----------|--------|--------|
| **True 0** | 5 603 | 334 |
| **True 1** | 243   | 5 820 |

---

## Limitations & Biases

- Relies only on free‑text invoice fields; numeric anomalies (e.g., price outliers) are out of scope.
- Trained on 2023 federal data; state/municipal or older invoices may need adaptation.
- False positives are expected; always corroborate with additional data.

---

## Ethical considerations

Use this model as an **assistant**, not a final verdict. Always corroborate predictions with official sanction registries.

---

## License

Released under the **Apache License 2.0**. This applies to weights, code and dataset scripts.

---

## Resources

* **GitHub** — source code, data‑processing notebooks and training logs: <https://github.com/CleitonOERocha/Mestrado>
* **Hugging Face** — model hub page: <https://huggingface.co/CleitonOERocha/deepseek-r1-distill-llama-8B-finetuned-nfe-detection>

---

## Citation

```bibtex
@mastersthesis{rocha2025nfe,
  author  = {Cleiton Otavio da Exaltação Rocha and Gecynalda Soares da Silva Gomes},
  title   = {Detection of Potentially Untrustworthy Companies through Government Procurement Extracts},
  school  = {Universidade Federal da Bahia},
  year    = {2025},
  address = {Salvador, Brasil}
}
```

---

### Contact

Open an issue on the [GitHub repo](https://github.com/CleitonOERocha/Mestrado) or tag **@CleitonOERocha** on the 🤗 Hub.

---