You can deploy this model and start earning money today!

Views

No views yet

algerian-law-marbert

A MARBERTv2 encoder domain-adapted on Algerian family-law text (Darja + MSA + Facebook legal Q&A), producing 768-dimensional embeddings for Algerian legal information retrieval.

Fine-tuned from UBC-NLP/MARBERTv2 with CachedMultipleNegativesRankingLoss on 1,000 (question → article) triplet pairs sourced from real Algerian Facebook legal-advice groups, aligned to the Algerian Family Code (Law No. 84-11). Queries are written in Darja (Algerian dialect) and Arabizi; documents are law articles in Modern Standard Arabic. This model is the shared backbone for the two-stage legal retrieval system:

Dense retriever: 81melody/algerian-law-biencoder-v2
Reranker: 81melody/algerian-law-reranker-v1


Architecture	MARBERTv2 (BERT-base, 768 dim, 12 layers)
Task	Semantic similarity / dense retrieval
Languages	Darja · Arabizi · MSA · Code-switched
Domain	Algerian family law (Droit de la famille algérien)
Training data	1,000 triplets from Facebook legal-advice groups
Best eval metric	cosine_accuracy = 0.741 (TripletEvaluator, 112-sample eval set)
License	Apache 2.0

Model Details

Model Description

Model Type: Sentence Transformer
Base model: UBC-NLP/MARBERTv2
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Supported Modality: Text

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'BertModel'})
  (1): Pooling({'embedding_dimension': 768, 'pooling_mode': 'mean', 'include_prompt': True})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
    'عندي اب تاعي ما عايش معانا ما يصرف عليها هرب وخلانا ويجي مشهر لشهر يسبنا ويسب الام تاعي ويروح مرضها رجعها تشرب دوا وتروح لطبيب تع اعصاب ومحبش يطلقها يقلها نخليها هكاك معلقة تتعذبي وزيد دورو ميمدهولناش انا وختي نقراو انا نخدم نصرف على روحي وختي وماما يصرف غليهم خويا مسكيت صغير عليا عمرو 20 سنة غير يبريكولي ولي يجيبها يحطهالنا حبيت نطلقها باش تتهنا منوا باسكو كرهلنا حياتنا هكا ميزيد يجي لينا ما يزيد يسبنا انا عندي سوتنونس عاذ لعام كرهلي حياتي مخااني نقرى ما هناني يضلي يعيطلي ويسب فيا ويرخس فيا نديرو روجوتي يزيد يعيطلي بنوامر وحدوخرين اعطوني حل كيفاه نرفد عليه طلاق لضرر',
    'المادة 53',
    'المادة 54',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.2787, 0.1867],
#         [0.2787, 1.0000, 0.4629],
#         [0.1867, 0.4629, 1.0000]])

Evaluation

Metrics

Triplet

Dataset: marbert_algerian_law_eval
Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.7411

Training Details

Training Dataset

Unnamed Dataset

Size: 1,000 training samples
Columns: anchor, positive, and negative
Approximate statistics based on the first 1000 samples:
anchor positive negative
type string string string
details
min: 9 tokens
mean: 57.4 tokens
max: 512 tokens
min: 4 tokens
mean: 4.81 tokens
max: 8 tokens
min: 4 tokens
mean: 4.0 tokens
max: 5 tokens

Samples:

anchor	positive	negative
`سلام عليكم حبا ندير باش يزيدوني في بدل الاجار كفاش ندير انا 600 مراهش تكفي لاكراء ولكراء راه غالي`	`المادة 79`	`المادة 80`
`سؤالي لأهل الاختصاص فقط...عندي عامين طلاق وطليقي لحد الآن ماعطانيش التعويض نتاع الطلاق وحق العدة....كيفاش نطالب بيهم...أعطوني جواب قانوني من فضلكم؟؟؟؟`	`المادة 61`	`المادة 79`
`عند زواج الأم هل القاضي يستدعي الاطفال لتخييرهم عند من يريدون البقاء عند امهم او ابيهم بإعتبار سن التميز 12 سنة وهل التنازل عن الحضانة للجدة ام الأم أثناء زواج الأم يمنع الأب من اخذ الحضانة`	`المادة 79`	`المادة 80`

Loss: CachedMultipleNegativesRankingLoss with these parameters:
json
1{ 2 "scale": 20.0, 3 "similarity_fct": "cos_sim", 4 "mini_batch_size": 32, 5 "gather_across_devices": false, 6 "directions": [ 7 "query_to_doc" 8 ], 9 "partition_mode": "joint", 10 "hardness_mode": null, 11 "hardness_strength": 0.0 12}

Evaluation Dataset

Unnamed Dataset

Size: 112 evaluation samples
Columns: anchor, positive, and negative
Approximate statistics based on the first 112 samples:
anchor positive negative
type string string string
details
min: 13 tokens
mean: 67.54 tokens
max: 418 tokens
min: 4 tokens
mean: 4.9 tokens
max: 8 tokens
min: 4 tokens
mean: 4.01 tokens
max: 5 tokens

Samples:

anchor	positive	negative
`سلام في طلاق تعسفي نقدر نقلو منطلقش لازم تديرلي داري وحدي نقدر نحكلو على مشاكل و بلي مش نحوس نتطلق`	`المادة 49`	`المادة 52`
`سلام وعليكم خاوتي بغيتكم ترشدوني نا قدمت طلب رجوع لبيت الزوجية للزوج وهو مبغاش رفع عليا زود خطرات قضية طلاق وميحضرش الجلسات ونا رحت شكيت بيه بشكوى الاهمال العائلي 10 ماي جلسة لاولى واليوم بلغني بلي رفع قضية طلاق جديده وضرك نقدر نشارعو بلاشي مندير محامي ونجيب حقي`	`المادة 48`	`المادة 55`
`فهموني فطلاق بالنشوز من فضلكم واسكو لمرا تسقط عليها الحضانة في هاذ لحالة ولا لا`	`المادة 67`	`المادة 66`

Loss: CachedMultipleNegativesRankingLoss with these parameters:
json
1{ 2 "scale": 20.0, 3 "similarity_fct": "cos_sim", 4 "mini_batch_size": 32, 5 "gather_across_devices": false, 6 "directions": [ 7 "query_to_doc" 8 ], 9 "partition_mode": "joint", 10 "hardness_mode": null, 11 "hardness_strength": 0.0 12}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 16
per_device_eval_batch_size: 16
learning_rate: 2e-05
num_train_epochs: 15
warmup_steps: 0.1
fp16: True

All Hyperparameters

Click to expand

do_predict: False
prediction_loss_only: True
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 2e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 15
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_ratio: None
warmup_steps: 0.1
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
enable_jit_checkpoint: False
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
use_cpu: False
seed: 42
data_seed: None
bf16: False
fp16: True
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: -1
ddp_backend: None
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: False
ignore_data_skip: False
fsdp: []
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
parallelism_config: None
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch_fused
optim_args: None
group_by_length: False
length_column_name: length
project: huggingface
trackio_space_id: trackio
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
dataloader_pin_memory: True
dataloader_persistent_workers: False
skip_memory_metrics: True
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
hub_revision: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_for_metrics: []
eval_do_concat_batches: True
auto_find_batch_size: False
full_determinism: False
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
include_num_input_tokens_seen: no
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: True
use_cache: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Framework Versions

Python: 3.12.13
Sentence Transformers: 5.4.1
Transformers: 5.0.0
PyTorch: 2.10.0+cu128
Accelerate: 1.13.0
Datasets: 4.0.0
Tokenizers: 0.22.2

Citation

BibTeX

Sentence Transformers

bibtex

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

CachedMultipleNegativesRankingLoss

bibtex

@misc{gao2021scaling,
    title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
    author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
    year={2021},
    eprint={2101.06983},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

	anchor	positive	negative
type	string	string	string
details	min: 9 tokens mean: 57.4 tokens max: 512 tokens	min: 4 tokens mean: 4.81 tokens max: 8 tokens	min: 4 tokens mean: 4.0 tokens max: 5 tokens

81melody/algerian-law-marbert

algerian-law-marbert

Model Details

Model Description

Model Sources

Full Model Architecture

Usage

Direct Usage (Sentence Transformers)

Evaluation

Metrics

Triplet

Training Details

Training Dataset

Unnamed Dataset

Evaluation Dataset

Unnamed Dataset

Training Hyperparameters

Non-Default Hyperparameters

All Hyperparameters

Framework Versions

Citation

BibTeX

Sentence Transformers

CachedMultipleNegativesRankingLoss

81melody/
algerian-law-marbert