Omartificial-Intelligence-Space's picture
update readme.md
6916465 verified
metadata
language:
  - ar
library_name: sentence-transformers
tags:
  - mteb
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:557850
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
metrics:
  - pearson_cosine
  - spearman_cosine
  - pearson_manhattan
  - spearman_manhattan
  - pearson_euclidean
  - spearman_euclidean
  - pearson_dot
  - spearman_dot
  - pearson_max
  - spearman_max
widget:
  - source_sentence: ذكر متوازن بعناية يقف على قدم واحدة بالقرب من منطقة شاطئ المحيط النظيفة
    sentences:
      - رجل يقدم عرضاً
      - هناك رجل بالخارج قرب الشاطئ
      - رجل يجلس على أريكه
  - source_sentence: رجل يقفز إلى سريره القذر
    sentences:
      - السرير قذر.
      - رجل يضحك أثناء غسيل الملابس
      - الرجل على القمر
  - source_sentence: الفتيات بالخارج
    sentences:
      - امرأة تلف الخيط إلى كرات بجانب كومة من الكرات
      - فتيان يركبان في جولة متعة
      - >-
        ثلاث فتيات يقفون سوية في غرفة واحدة تستمع وواحدة تكتب على الحائط
        والثالثة تتحدث إليهن
  - source_sentence: الرجل يرتدي قميصاً أزرق.
    sentences:
      - >-
        رجل يرتدي قميصاً أزرق يميل إلى الجدار بجانب الطريق مع شاحنة زرقاء وسيارة
        حمراء مع الماء في الخلفية.
      - كتاب القصص مفتوح
      - رجل يرتدي قميص أسود يعزف على الجيتار.
  - source_sentence: يجلس شاب ذو شعر أشقر على الحائط يقرأ جريدة بينما تمر امرأة وفتاة شابة.
    sentences:
      - ذكر شاب ينظر إلى جريدة بينما تمر إمرأتان بجانبه
      - رجل يستلقي على وجهه على مقعد في الحديقة.
      - الشاب نائم بينما الأم تقود ابنتها إلى الحديقة
pipeline_tag: sentence-similarity
model-index:
  - name: Omartificial-Intelligence-Space/Arabic-MiniLM-L12-v2-all-nli-triplet
    results:
      - dataset:
          config: default
          name: MTEB BIOSSES (default)
          revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
          split: test
          type: mteb/biosses-sts
        metrics:
          - type: cosine_pearson
            value: 72.5081840952171
          - type: cosine_spearman
            value: 69.41362982941537
          - type: euclidean_pearson
            value: 67.45121490183709
          - type: euclidean_spearman
            value: 67.15273493989758
          - type: main_score
            value: 69.41362982941537
          - type: manhattan_pearson
            value: 67.6119022794479
          - type: manhattan_spearman
            value: 67.51659865246586
        task:
          type: STS
      - dataset:
          config: default
          name: MTEB SICK-R (default)
          revision: 20a6d6f312dd54037fe07a32d58e5e168867909d
          split: test
          type: mteb/sickr-sts
        metrics:
          - type: cosine_pearson
            value: 83.61591268324493
          - type: cosine_spearman
            value: 79.61914245705792
          - type: euclidean_pearson
            value: 81.32044881859483
          - type: euclidean_spearman
            value: 79.04866675279919
          - type: main_score
            value: 79.61914245705792
          - type: manhattan_pearson
            value: 81.09220518201322
          - type: manhattan_spearman
            value: 78.87590523907905
        task:
          type: STS
      - dataset:
          config: default
          name: MTEB STS12 (default)
          revision: a0d554a64d88156834ff5ae9920b964011b16384
          split: test
          type: mteb/sts12-sts
        metrics:
          - type: cosine_pearson
            value: 84.59807803376341
          - type: cosine_spearman
            value: 77.38689922564416
          - type: euclidean_pearson
            value: 83.92034850646732
          - type: euclidean_spearman
            value: 76.75857193093438
          - type: main_score
            value: 77.38689922564416
          - type: manhattan_pearson
            value: 83.97191863964667
          - type: manhattan_spearman
            value: 76.89790070725708
        task:
          type: STS
      - dataset:
          config: default
          name: MTEB STS13 (default)
          revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca
          split: test
          type: mteb/sts13-sts
        metrics:
          - type: cosine_pearson
            value: 78.18664268536664
          - type: cosine_spearman
            value: 79.58989311630421
          - type: euclidean_pearson
            value: 79.25259731614729
          - type: euclidean_spearman
            value: 80.1701122827397
          - type: main_score
            value: 79.58989311630421
          - type: manhattan_pearson
            value: 79.12601451996869
          - type: manhattan_spearman
            value: 79.98999436073663
        task:
          type: STS
      - dataset:
          config: default
          name: MTEB STS14 (default)
          revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375
          split: test
          type: mteb/sts14-sts
        metrics:
          - type: cosine_pearson
            value: 80.97541876658141
          - type: cosine_spearman
            value: 79.78614320477877
          - type: euclidean_pearson
            value: 81.01514505747167
          - type: euclidean_spearman
            value: 80.73664735567839
          - type: main_score
            value: 79.78614320477877
          - type: manhattan_pearson
            value: 80.8746560526314
          - type: manhattan_spearman
            value: 80.67025673179079
        task:
          type: STS
      - dataset:
          config: default
          name: MTEB STS15 (default)
          revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3
          split: test
          type: mteb/sts15-sts
        metrics:
          - type: cosine_pearson
            value: 85.23661155813113
          - type: cosine_spearman
            value: 86.21134464371615
          - type: euclidean_pearson
            value: 85.82518684522182
          - type: euclidean_spearman
            value: 86.43600784349509
          - type: main_score
            value: 86.21134464371615
          - type: manhattan_pearson
            value: 85.83101152371589
          - type: manhattan_spearman
            value: 86.42228695679498
        task:
          type: STS
      - dataset:
          config: default
          name: MTEB STS16 (default)
          revision: 4d8694f8f0e0100860b497b999b3dbed754a0513
          split: test
          type: mteb/sts16-sts
        metrics:
          - type: cosine_pearson
            value: 79.20106689077852
          - type: cosine_spearman
            value: 81.39570893867825
          - type: euclidean_pearson
            value: 80.39578888768929
          - type: euclidean_spearman
            value: 81.19950443340412
          - type: main_score
            value: 81.39570893867825
          - type: manhattan_pearson
            value: 80.2226679341839
          - type: manhattan_spearman
            value: 80.99142422593823
        task:
          type: STS
      - dataset:
          config: ar-ar
          name: MTEB STS17 (ar-ar)
          revision: faeb762787bd10488a50c8b5be4a3b82e411949c
          split: test
          type: mteb/sts17-crosslingual-sts
        metrics:
          - type: cosine_pearson
            value: 81.05294851623468
          - type: cosine_spearman
            value: 81.10570655134113
          - type: euclidean_pearson
            value: 79.22292773537778
          - type: euclidean_spearman
            value: 78.84204232638425
          - type: main_score
            value: 81.10570655134113
          - type: manhattan_pearson
            value: 79.43750460320484
          - type: manhattan_spearman
            value: 79.33713593557482
        task:
          type: STS
      - dataset:
          config: ar
          name: MTEB STS22 (ar)
          revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
          split: test
          type: mteb/sts22-crosslingual-sts
        metrics:
          - type: cosine_pearson
            value: 45.96875498680092
          - type: cosine_spearman
            value: 52.405509117149904
          - type: euclidean_pearson
            value: 42.097450896728226
          - type: euclidean_spearman
            value: 50.89022884113707
          - type: main_score
            value: 52.405509117149904
          - type: manhattan_pearson
            value: 42.22827727075534
          - type: manhattan_spearman
            value: 50.912841055442634
        task:
          type: STS
      - dataset:
          config: default
          name: MTEB STSBenchmark (default)
          revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
          split: test
          type: mteb/stsbenchmark-sts
        metrics:
          - type: cosine_pearson
            value: 83.13261516884116
          - type: cosine_spearman
            value: 84.3492527221498
          - type: euclidean_pearson
            value: 82.691603178401
          - type: euclidean_spearman
            value: 83.0499566200785
          - type: main_score
            value: 84.3492527221498
          - type: manhattan_pearson
            value: 82.68307441014618
          - type: manhattan_spearman
            value: 83.01315787964519
        task:
          type: STS
      - dataset:
          config: default
          name: MTEB SummEval (default)
          revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c
          split: test
          type: mteb/summeval
        metrics:
          - type: cosine_pearson
            value: 31.149232235402845
          - type: cosine_spearman
            value: 30.685504130606255
          - type: dot_pearson
            value: 27.466307571160375
          - type: dot_spearman
            value: 28.93064261485915
          - type: main_score
            value: 30.685504130606255
          - type: pearson
            value: 31.149232235402845
          - type: spearman
            value: 30.685504130606255
        task:
          type: Summarization
  - name: >-
      SentenceTransformer based on
      sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 256
          type: sts-test-256
        metrics:
          - type: pearson_cosine
            value: 0.8264447022356382
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8386403752382455
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8219134931449013
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.825509659109493
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8223094468630248
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8260503151751462
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.6375226884845725
            name: Pearson Dot
          - type: spearman_dot
            value: 0.6287228614640888
            name: Spearman Dot
          - type: pearson_max
            value: 0.8264447022356382
            name: Pearson Max
          - type: spearman_max
            value: 0.8386403752382455
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 128
          type: sts-test-128
        metrics:
          - type: pearson_cosine
            value: 0.8209661910768973
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8347149482673766
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8082811559854036
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8148314269262763
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8093138512113149
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8156468458613929
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.5795109620454884
            name: Pearson Dot
          - type: spearman_dot
            value: 0.5760223026552876
            name: Spearman Dot
          - type: pearson_max
            value: 0.8209661910768973
            name: Pearson Max
          - type: spearman_max
            value: 0.8347149482673766
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 64
          type: sts-test-64
        metrics:
          - type: pearson_cosine
            value: 0.808708530451336
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8217532539767914
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.7876121380998453
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.7969092304137347
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.7902997966909958
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.7987635968785215
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.495047136234386
            name: Pearson Dot
          - type: spearman_dot
            value: 0.49287000679901516
            name: Spearman Dot
          - type: pearson_max
            value: 0.808708530451336
            name: Pearson Max
          - type: spearman_max
            value: 0.8217532539767914
            name: Spearman Max
license: apache-2.0
datasets:
  - Omartificial-Intelligence-Space/Arabic-NLi-Triplet

SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

This is a sentence-transformers model finetuned from sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 on the Omartificial-Intelligence-Space/arabic-n_li-triplet dataset. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

Model Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, '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.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("Omartificial-Intelligence-Space/MiniLM-L12-v2-all-nli-triplet")
# Run inference
sentences = [
    'يجلس شاب ذو شعر أشقر على الحائط يقرأ جريدة بينما تمر امرأة وفتاة شابة.',
    'ذكر شاب ينظر إلى جريدة بينما تمر إمرأتان بجانبه',
    'الشاب نائم بينما الأم تقود ابنتها إلى الحديقة',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Semantic Similarity

Metric Value
pearson_cosine 0.8264
spearman_cosine 0.8386
pearson_manhattan 0.8219
spearman_manhattan 0.8255
pearson_euclidean 0.8223
spearman_euclidean 0.8261
pearson_dot 0.6375
spearman_dot 0.6287
pearson_max 0.8264
spearman_max 0.8386

Semantic Similarity

Metric Value
pearson_cosine 0.821
spearman_cosine 0.8347
pearson_manhattan 0.8083
spearman_manhattan 0.8148
pearson_euclidean 0.8093
spearman_euclidean 0.8156
pearson_dot 0.5795
spearman_dot 0.576
pearson_max 0.821
spearman_max 0.8347

Semantic Similarity

Metric Value
pearson_cosine 0.8087
spearman_cosine 0.8218
pearson_manhattan 0.7876
spearman_manhattan 0.7969
pearson_euclidean 0.7903
spearman_euclidean 0.7988
pearson_dot 0.495
spearman_dot 0.4929
pearson_max 0.8087
spearman_max 0.8218

Training Details

Training Dataset

Omartificial-Intelligence-Space/arabic-n_li-triplet

  • Dataset: Omartificial-Intelligence-Space/arabic-n_li-triplet
  • Size: 557,850 training samples
  • Columns: anchor, positive, and negative
  • Approximate statistics based on the first 1000 samples:
    anchor positive negative
    type string string string
    details
    • min: 5 tokens
    • mean: 10.33 tokens
    • max: 52 tokens
    • min: 5 tokens
    • mean: 13.21 tokens
    • max: 49 tokens
    • min: 5 tokens
    • mean: 15.32 tokens
    • max: 53 tokens
  • Samples:
    anchor positive negative
    شخص على حصان يقفز فوق طائرة معطلة شخص في الهواء الطلق، على حصان. شخص في مطعم، يطلب عجة.
    أطفال يبتسمون و يلوحون للكاميرا هناك أطفال حاضرون الاطفال يتجهمون
    صبي يقفز على لوح التزلج في منتصف الجسر الأحمر. الفتى يقوم بخدعة التزلج الصبي يتزلج على الرصيف
  • Loss: MatryoshkaLoss with these parameters:
    {
        "loss": "MultipleNegativesRankingLoss",
        "matryoshka_dims": [
            256,
            128,
            64
        ],
        "matryoshka_weights": [
            1,
            1,
            1
        ],
        "n_dims_per_step": -1
    }
    

Evaluation Dataset

Omartificial-Intelligence-Space/arabic-n_li-triplet

  • Dataset: Omartificial-Intelligence-Space/arabic-n_li-triplet
  • Size: 6,584 evaluation samples
  • Columns: anchor, positive, and negative
  • Approximate statistics based on the first 1000 samples:
    anchor positive negative
    type string string string
    details
    • min: 5 tokens
    • mean: 21.86 tokens
    • max: 105 tokens
    • min: 4 tokens
    • mean: 10.22 tokens
    • max: 49 tokens
    • min: 4 tokens
    • mean: 11.2 tokens
    • max: 33 tokens
  • Samples:
    anchor positive negative
    امرأتان يتعانقان بينما يحملان حزمة إمرأتان يحملان حزمة الرجال يتشاجرون خارج مطعم
    طفلين صغيرين يرتديان قميصاً أزرق، أحدهما يرتدي الرقم 9 والآخر يرتدي الرقم 2 يقفان على خطوات خشبية في الحمام ويغسلان أيديهما في المغسلة. طفلين يرتديان قميصاً مرقماً يغسلون أيديهم طفلين يرتديان سترة يذهبان إلى المدرسة
    رجل يبيع الدونات لعميل خلال معرض عالمي أقيم في مدينة أنجليس رجل يبيع الدونات لعميل امرأة تشرب قهوتها في مقهى صغير
  • Loss: MatryoshkaLoss with these parameters:
    {
        "loss": "MultipleNegativesRankingLoss",
        "matryoshka_dims": [
            256,
            128,
            64
        ],
        "matryoshka_weights": [
            1,
            1,
            1
        ],
        "n_dims_per_step": -1
    }
    

Training Hyperparameters

Non-Default Hyperparameters

  • per_device_train_batch_size: 64
  • per_device_eval_batch_size: 64
  • num_train_epochs: 1
  • warmup_ratio: 0.1
  • fp16: True
  • batch_sampler: no_duplicates

All Hyperparameters

Click to expand
  • overwrite_output_dir: False
  • do_predict: False
  • prediction_loss_only: True
  • per_device_train_batch_size: 64
  • per_device_eval_batch_size: 64
  • per_gpu_train_batch_size: None
  • per_gpu_eval_batch_size: None
  • gradient_accumulation_steps: 1
  • eval_accumulation_steps: None
  • learning_rate: 5e-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: 1
  • max_steps: -1
  • lr_scheduler_type: linear
  • lr_scheduler_kwargs: {}
  • warmup_ratio: 0.1
  • warmup_steps: 0
  • log_level: passive
  • log_level_replica: warning
  • log_on_each_node: True
  • logging_nan_inf_filter: True
  • save_safetensors: True
  • save_on_each_node: False
  • save_only_model: False
  • no_cuda: False
  • use_cpu: False
  • use_mps_device: False
  • seed: 42
  • data_seed: None
  • jit_mode_eval: False
  • use_ipex: False
  • bf16: False
  • fp16: True
  • fp16_opt_level: O1
  • half_precision_backend: auto
  • bf16_full_eval: False
  • fp16_full_eval: False
  • tf32: None
  • local_rank: 0
  • ddp_backend: None
  • tpu_num_cores: None
  • tpu_metrics_debug: False
  • debug: []
  • dataloader_drop_last: False
  • dataloader_num_workers: 0
  • dataloader_prefetch_factor: None
  • past_index: -1
  • disable_tqdm: False
  • remove_unused_columns: True
  • label_names: None
  • load_best_model_at_end: False
  • ignore_data_skip: False
  • fsdp: []
  • fsdp_min_num_params: 0
  • fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
  • fsdp_transformer_layer_cls_to_wrap: None
  • accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'gradient_accumulation_kwargs': None}
  • deepspeed: None
  • label_smoothing_factor: 0.0
  • optim: adamw_torch
  • optim_args: None
  • adafactor: False
  • group_by_length: False
  • length_column_name: length
  • 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
  • use_legacy_prediction_loop: False
  • push_to_hub: False
  • resume_from_checkpoint: None
  • hub_model_id: None
  • hub_strategy: every_save
  • hub_private_repo: False
  • hub_always_push: False
  • gradient_checkpointing: False
  • gradient_checkpointing_kwargs: None
  • include_inputs_for_metrics: False
  • eval_do_concat_batches: True
  • fp16_backend: auto
  • push_to_hub_model_id: None
  • push_to_hub_organization: None
  • mp_parameters:
  • auto_find_batch_size: False
  • full_determinism: False
  • torchdynamo: None
  • ray_scope: last
  • ddp_timeout: 1800
  • torch_compile: False
  • torch_compile_backend: None
  • torch_compile_mode: None
  • dispatch_batches: None
  • split_batches: None
  • include_tokens_per_second: False
  • include_num_input_tokens_seen: False
  • neftune_noise_alpha: None
  • optim_target_modules: None
  • batch_sampler: no_duplicates
  • multi_dataset_batch_sampler: proportional

Training Logs

Epoch Step Training Loss sts-test-128_spearman_cosine sts-test-256_spearman_cosine sts-test-64_spearman_cosine
0.0229 200 6.2204 - - -
0.0459 400 4.9559 - - -
0.0688 600 4.7835 - - -
0.0918 800 4.2725 - - -
0.1147 1000 4.291 - - -
0.1377 1200 4.0704 - - -
0.1606 1400 3.7962 - - -
0.1835 1600 3.7447 - - -
0.2065 1800 3.569 - - -
0.2294 2000 3.5373 - - -
0.2524 2200 3.608 - - -
0.2753 2400 3.5609 - - -
0.2983 2600 3.5231 - - -
0.3212 2800 3.3312 - - -
0.3442 3000 3.4803 - - -
0.3671 3200 3.3552 - - -
0.3900 3400 3.3024 - - -
0.4130 3600 3.2559 - - -
0.4359 3800 3.1882 - - -
0.4589 4000 3.227 - - -
0.4818 4200 3.0889 - - -
0.5048 4400 3.0861 - - -
0.5277 4600 3.0178 - - -
0.5506 4800 3.231 - - -
0.5736 5000 3.1593 - - -
0.5965 5200 3.1101 - - -
0.6195 5400 3.1307 - - -
0.6424 5600 3.1265 - - -
0.6654 5800 3.1116 - - -
0.6883 6000 3.1417 - - -
0.7113 6200 3.0862 - - -
0.7342 6400 2.9652 - - -
0.7571 6600 2.8466 - - -
0.7801 6800 2.271 - - -
0.8030 7000 2.046 - - -
0.8260 7200 1.9634 - - -
0.8489 7400 1.8875 - - -
0.8719 7600 1.7655 - - -
0.8948 7800 1.6874 - - -
0.9177 8000 1.7315 - - -
0.9407 8200 1.6674 - - -
0.9636 8400 1.6574 - - -
0.9866 8600 1.6142 - - -
1.0 8717 - 0.8347 0.8386 0.8218

Framework Versions

  • Python: 3.9.18
  • Sentence Transformers: 3.0.1
  • Transformers: 4.40.0
  • PyTorch: 2.2.2+cu121
  • Accelerate: 0.26.1
  • Datasets: 2.19.0
  • Tokenizers: 0.19.1

Citation

BibTeX

Sentence Transformers

@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",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning}, 
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply}, 
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

Acknowledgments

The author would like to thank Prince Sultan University for their invaluable support in this project. Their contributions and resources have been instrumental in the development and fine-tuning of these models.

## Citation

If you use the Arabic Matryoshka Embeddings Model, please cite it as follows:

```bibtex
@software{nacar2024,
  author       = {Omer Nacar},
  title        = {Arabic Matryoshka Embeddings Model - Arabic MiniLM L12 v2 All Nli Triplet},
  year         = 2024,
  url          = {https://huggingface.co/Omartificial-Intelligence-Space/Arabic-MiniLM-L12-v2-all-nli-triplet},
  version      = {1.0.0},
}