This is a sentence-transformers model finetuned from BAAI/bge-m3. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for retrieval.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: BAAI/bge-m3
Maximum Sequence Length: 8192 tokens
Output Dimensionality: 1024 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': 'XLMRobertaModel'})
  (1): Pooling({'embedding_dimension': 1024, 'pooling_mode': 'cls', 'include_prompt': True})
  (2): Normalize({})
)

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("expri34/beyan-quran-bge-m3")
# Run inference
sentences = [
    "De ki, Allah'a ve Peygamber'e itaat edin! Eğer aksine giderlerse, şüphe yok ki Allah kâfirleri sevmez.",
    "De ki, Allah'a ve Peygamber'e itaat edin! Eğer aksine giderlerse, şüphe yok ki Allah kâfirleri sevmez. 31- De ki: “Eğer Allah’ı seviyorsanız Bana uyun ki Allah da sizi sevsin ve günahlarınızı bağışlasın. Allah Ğafurdur, Rahimdir.” 32- De ki: “Allah’a ve Rasûl’e itaat edin.” Eğer yüz çevirirlerse bilsinler ki Allah kâfirleri sevmez. 31. Bu âyet Allah’ı gerçek anlamı ile sevenler ile bunu mücerred bir iddia olarak ileri sürenlerin kendisi vasıtası ile bilinip ayırt edildiği bir ölçüdür. Zira Allah’ı sevmenin alâmeti Muhammed sallallahu aleyhi ve sellem’e tabi olmaktır. Yüce Allah O’na ve O’nun dave",
    'فَبَدَّلَ الَّذِينَ ظَلَمُوا قَوْلًا غَيْرَ الَّذِي قِيلَ لَهُمْ فَأَنْزَلْنَا عَلَى الَّذِينَ ظَلَمُوا رِجْزًا مِنَ السَّمَاءِ بِمَا كَانُوا يَفْسُقُونَ',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.7001, 0.1396],
#         [0.7001, 1.0000, 0.0754],
#         [0.1396, 0.0754, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

Size: 29,923 training samples
Columns: anchor and positive
Approximate statistics based on the first 1000 samples:
anchor positive
type string string
details
min: 3 tokens
mean: 36.61 tokens
max: 405 tokens
min: 3 tokens
mean: 80.45 tokens
max: 622 tokens

Samples:

anchor	positive
`Nereden (yola) çıkarsan, yüzünü Mescid-i Haram'a doğru çevir. Siz de nerede olursanız, yüzünüzü o yana döndürün, Ta ki, zalim olanlardan başka insanların aleyhinizde bir delili bulunmasın. Artık onlar`	`zulüm`
`إِنْ يَنْصُرْكُمُ اللَّهُ فَلَا غَالِبَ لَكُمْ ۖ وَإِنْ يَخْذُلْكُمْ فَمَنْ ذَا الَّذِي يَنْصُرُكُمْ مِنْ بَعْدِهِ ۗ وَعَلَى اللَّهِ فَلْيَتَوَكَّلِ الْمُؤْمِنُونَ`	`Allah size yardım ederse, sizi yenecek yoktur. Eğer sizi yardımsız bırakırsa, artık ondan sonra size kim yardım edebilir? Müminler ancak Allah'a güvenip dayansınlar.`
`وَيْلٌ يَوْمَئِذٍ لِلْمُكَذِّبِينَ`	`O gün yalanlayanların vay haline!`

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

Evaluation Dataset

Unnamed Dataset

Size: 5,280 evaluation samples
Columns: anchor and positive
Approximate statistics based on the first 1000 samples:
anchor positive
type string string
details
min: 3 tokens
mean: 38.43 tokens
max: 404 tokens
min: 3 tokens
mean: 80.54 tokens
max: 622 tokens

Samples:

anchor	positive
`ibrahim ile ilgili Kuran ne diyor`	`Bir de dedi ki: "Ben Rabbime gidiyorum, o bana yolunu gösterir."`
`(Onlar mı hayırlı) yoksa, kendine yalvardığı zaman bunalmışa karşılık veren ve başındaki sıkıntıyı gideren, sizi yeryüzünün hakimleri yapan mı? Allah'ın yanında başka bir ilâh mı var? Ne kıt düşünüyorsunuz!`	`أَمَّنْ يُجِيبُ الْمُضْطَرَّ إِذَا دَعَاهُ وَيَكْشِفُ السُّوءَ وَيَجْعَلُكُمْ خُلَفَاءَ الْأَرْضِ ۗ أَإِلَٰهٌ مَعَ اللَّهِ ۚ قَلِيلًا مَا تَذَكَّرُونَ`
`Çünkü gündüz senin için uzun bir meşguliyet vardır.`	Çünkü gündüz senin için uzun bir meşguliyet vardır. 1- Ey elbisesine sarınıp bürünen! 2- Kalk ve birazı müstesnâ geceyi namazla geçir; 3- Yarısını veya ondan biraz azını. 4- Yahut da ondan biraz fazlasını. Kur’ân’ı da tertil üzere (ağır ağır ve tane tane) oku. 5- Şüphesiz Biz sana ağır bir söz vahyedeceğiz. 6- Çünkü gece kalkışı hem daha etkilidir hem de ondaki okuyuş daha düzgün ve sağlamdır. 7- Gündüz vakti ise senin uzun uğraşların vardır. 8- Rabbinin ismini an ve her şeyden yüz çevirip tamamiyle O’na yönel! 9- O, doğunun da batının da Rabbidi

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

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 4
num_train_epochs: 1
learning_rate: 2e-06
warmup_steps: 0.1
gradient_accumulation_steps: 8
fp16: True
eval_strategy: steps
per_device_eval_batch_size: 4

All Hyperparameters

Click to expand

per_device_train_batch_size: 4
num_train_epochs: 1
max_steps: -1
learning_rate: 2e-06
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_steps: 0.1
optim: adamw_torch
optim_args: None
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
optim_target_modules: None
gradient_accumulation_steps: 8
average_tokens_across_devices: True
max_grad_norm: 1.0
label_smoothing_factor: 0.0
bf16: False
fp16: True
bf16_full_eval: False
fp16_full_eval: False
tf32: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
use_liger_kernel: False
liger_kernel_config: None
use_cache: False
neftune_noise_alpha: None
torch_empty_cache_steps: None
auto_find_batch_size: False
log_on_each_node: True
logging_nan_inf_filter: True
include_num_input_tokens_seen: no
log_level: passive
log_level_replica: warning
disable_tqdm: False
project: huggingface
trackio_space_id: trackio
eval_strategy: steps
per_device_eval_batch_size: 4
prediction_loss_only: True
eval_on_start: False
eval_do_concat_batches: True
eval_use_gather_object: False
eval_accumulation_steps: None
include_for_metrics: []
batch_eval_metrics: False
save_only_model: False
save_on_each_node: False
enable_jit_checkpoint: False
push_to_hub: False
hub_private_repo: None
hub_model_id: None
hub_strategy: every_save
hub_always_push: False
hub_revision: None
load_best_model_at_end: False
ignore_data_skip: False
restore_callback_states_from_checkpoint: False
full_determinism: False
seed: 42
data_seed: None
use_cpu: 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
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_pin_memory: True
dataloader_persistent_workers: False
dataloader_prefetch_factor: None
remove_unused_columns: True
label_names: None
train_sampling_strategy: random
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
ddp_backend: None
ddp_timeout: 1800
fsdp: []
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
deepspeed: None
debug: []
skip_memory_metrics: True
do_predict: False
resume_from_checkpoint: None
warmup_ratio: None
local_rank: -1
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	Validation Loss
0.0267	25	0.6327	-
0.0535	50	0.6013	-
0.0802	75	0.5523	-
0.1069	100	0.4702	-
0.1337	125	0.4084	-
0.1604	150	0.3759	-
0.1871	175	0.3413	-
0.2139	200	0.3640	0.2953
0.2406	225	0.3196	-
0.2673	250	0.3098	-
0.2941	275	0.3359	-
0.3208	300	0.2916	-
0.3475	325	0.2713	-
0.3743	350	0.2880	-
0.4010	375	0.2857	-
0.4278	400	0.2396	0.2214
0.4545	425	0.2703	-
0.4812	450	0.2682	-
0.5080	475	0.2667	-
0.5347	500	0.2973	-
0.5614	525	0.2358	-
0.5882	550	0.2250	-
0.6149	575	0.2793	-
0.6416	600	0.2027	0.1898
0.6684	625	0.2154	-
0.6951	650	0.2038	-
0.7218	675	0.2249	-
0.7486	700	0.2530	-
0.7753	725	0.2012	-
0.8020	750	0.1971	-
0.8288	775	0.2232	-
0.8555	800	0.2477	0.1758
0.8822	825	0.2183	-
0.9090	850	0.2151	-
0.9357	875	0.1801	-
0.9624	900	0.1969	-
0.9892	925	0.1977	-
1.0	936	-	0.1730

Training Time

Training: 30.3 minutes
Evaluation: 9.0 minutes
Total: 39.4 minutes

Framework Versions

Python: 3.11.9
Sentence Transformers: 5.4.0
Transformers: 5.5.3
PyTorch: 2.6.0+cu124
Accelerate: 1.13.0
Datasets: 4.8.4
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",
}

MultipleNegativesRankingLoss

bibtex

@misc{oord2019representationlearningcontrastivepredictive,
      title={Representation Learning with Contrastive Predictive Coding},
      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
      year={2019},
      eprint={1807.03748},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/1807.03748},
}

	anchor	positive
type	string	string
details	min: 3 tokens mean: 36.61 tokens max: 405 tokens	min: 3 tokens mean: 80.45 tokens max: 622 tokens