ngdangkhanh/vietnamese-law-rerank-model

Model Card for Model ID

Model Details

Model Description

Vietnamese Law Rerank Model

📌 Giới thiệu

Đây là mô hình reranker được fine-tune cho ngữ cảnh pháp luật Việt Nam.
Model gốc: Alibaba-NLP/gte-multilingual-reranker-base.

Mục tiêu: cải thiện khả năng đánh giá mức độ liên quan giữa câu hỏi pháp luật (query) và đoạn luật (document).

---

📊 Dữ liệu huấn luyện

• Nguồn: anti-ai/ViNLI-Zalo-supervised
• Loại: Natural Language Inference (NLI) dạng supervised.
• Cách dùng: chuyển đổi thành cặp (query, document) với nhãn nhị phân:
  • entailment → liên quan (1)
  • contradiction / neutral → không liên quan (0)

Dữ liệu được chọn lọc và áp dụng cho bối cảnh pháp luật Việt Nam.

---

⚙️ Thông số huấn luyện

Tham số	Giá trị
Optimizer	AdamW (torch)
Learning rate	2e-5
Scheduler	Linear
Batch size (train/eval)	8
Gradient accumulation	8
Epochs	10 (early stop tại epoch 4)
Weight decay	0.25
Warmup ratio	0.2
Mixed precision	FP16
Max grad norm	0.6
Group by length	True
Report	Weights & Biases (wandb)
Early stopping patience	3

---

📈 Kết quả huấn luyện

Train Output

• Global step: 3340
• Training loss: 0.0208
• Train runtime: 14190s (~3.9h)
• Samples/s: 37.65

Evaluation (epoch 4, best checkpoint)

Metric	Giá trị
Eval loss	0.0028
Accuracy	0.9895
Precision	0.9798
Recall	1.0000
F1	0.9898
Runtime	133s
Samples/s	49.48

👉 Mô hình đạt độ chính xác gần 99%, cho thấy khả năng phân biệt đoạn luật liên quan rất tốt.

---

💻 Cách sử dụng

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

# Load model & tokenizer
tokenizer = AutoTokenizer.from_pretrained("your_username/vietnamese-legal-reranker")
model = AutoModelForSequenceClassification.from_pretrained("your_username/vietnamese-legal-reranker")

# Ví dụ
query = "Người lao động có quyền nghỉ thai sản bao lâu?"
document = "Theo điều 139 Bộ luật Lao động 2019, lao động nữ được nghỉ trước và sau khi sinh con là 6 tháng."

# Tokenize
inputs = tokenizer(query, document, return_tensors="pt", truncation=True, padding=True)

# Predict score
with torch.no_grad():
    outputs = model(**inputs)
    score = torch.sigmoid(outputs.logits.squeeze()).item()

print("Relevance score:", score)



- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** ['vi']
- **License:** apache-2.0
- **Finetuned from model [optional]:** [More Information Needed]

### Model Sources [optional]

<!-- Provide the basic links for the model. -->

- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]

## Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

### Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

[More Information Needed]

### Downstream Use [optional]

<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->

[More Information Needed]

### Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

[More Information Needed]

## Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

[More Information Needed]

### Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

## How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

## Training Details

### Training Data

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

[More Information Needed]

### Training Procedure

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

#### Preprocessing [optional]

[More Information Needed]


#### Training Hyperparameters

- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->

#### Speeds, Sizes, Times [optional]

<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->

[More Information Needed]

## Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

### Testing Data, Factors & Metrics

#### Testing Data

<!-- This should link to a Dataset Card if possible. -->

[More Information Needed]

#### Factors

<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->

[More Information Needed]

#### Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

[More Information Needed]

### Results

[More Information Needed]

#### Summary



## Model Examination [optional]

<!-- Relevant interpretability work for the model goes here -->

[More Information Needed]

## Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).

- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]

## Technical Specifications [optional]

### Model Architecture and Objective

[More Information Needed]

### Compute Infrastructure

[More Information Needed]

#### Hardware

[More Information Needed]

#### Software

[More Information Needed]

## Citation [optional]

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

**BibTeX:**

[More Information Needed]

**APA:**

[More Information Needed]

## Glossary [optional]

<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->

[More Information Needed]

## More Information [optional]

[More Information Needed]

## Model Card Authors [optional]

[More Information Needed]

## Model Card Contact

[More Information Needed]