base_model:

• aubmindlab/bert-base-arabertv02 language:
• ar model-index:
• name: omarelshehy/Arabic-Retrieval-v1.0 results:
  • dataset: config: ar name: MTEB MIRACLRetrieval (ar) revision: main split: dev type: miracl/mmteb-miracl metrics:
    • type: main_score value: 58.664
    • type: map_at_1 value: 32.399
    • type: map_at_10 value: 50.236000000000004
    • type: map_at_100 value: 51.87199999999999
    • type: map_at_1000 value: 51.926
    • type: ndcg_at_1 value: 48.376999999999995
    • type: ndcg_at_10 value: 58.664
    • type: ndcg_at_100 value: 63.754999999999995
    • type: ndcg_at_1000 value: 64.672
    • type: ndcg_at_20 value: 61.111000000000004
    • type: ndcg_at_3 value: 51.266
    • type: ndcg_at_5 value: 54.529 task: type: Retrieval
  • dataset: config: ar name: MTEB MIRACLRetrievalHardNegatives (ar) revision: 95c8db7d4a6e9c1d8a60601afd63d553ae20a2eb split: dev type: mteb/miracl-hard-negatives metrics:
    • type: main_score value: 60.026
    • type: map_at_1 value: 32.547
    • type: map_at_10 value: 51.345
    • type: map_at_100 value: 53.190000000000005
    • type: map_at_1000 value: 53.237
    • type: ndcg_at_1 value: 48.3
    • type: ndcg_at_10 value: 60.026
    • type: ndcg_at_100 value: 65.62400000000001
    • type: ndcg_at_1000 value: 66.282
    • type: ndcg_at_20 value: 62.856
    • type: ndcg_at_3 value: 52.1
    • type: ndcg_at_5 value: 55.627 task: type: Retrieval
  • dataset: config: ara-ara name: MTEB MLQARetrieval (ara-ara) revision: 397ed406c1a7902140303e7faf60fff35b58d285 split: test type: facebook/mlqa metrics:
    • type: main_score value: 56.032000000000004
    • type: map_at_1 value: 45.218
    • type: map_at_10 value: 52.32599999999999
    • type: map_at_100 value: 53.001
    • type: map_at_1000 value: 53.047999999999995
    • type: ndcg_at_1 value: 45.228
    • type: ndcg_at_10 value: 56.032000000000004
    • type: ndcg_at_100 value: 59.486000000000004
    • type: ndcg_at_1000 value: 60.938
    • type: ndcg_at_20 value: 57.507
    • type: ndcg_at_3 value: 52.05800000000001
    • type: ndcg_at_5 value: 54.005 task: type: Retrieval
  • dataset: config: ara-ara name: MTEB MLQARetrieval (ara-ara) revision: 397ed406c1a7902140303e7faf60fff35b58d285 split: validation type: facebook/mlqa metrics:
    • type: main_score value: 71.11
    • type: map_at_1 value: 58.221000000000004
    • type: map_at_10 value: 67.089
    • type: map_at_100 value: 67.62700000000001
    • type: map_at_1000 value: 67.648
    • type: ndcg_at_1 value: 58.221000000000004
    • type: ndcg_at_10 value: 71.11
    • type: ndcg_at_100 value: 73.824
    • type: ndcg_at_1000 value: 74.292
    • type: ndcg_at_20 value: 72.381
    • type: ndcg_at_3 value: 67.472
    • type: ndcg_at_5 value: 69.803 task: type: Retrieval
  • dataset: config: ar name: MTEB MintakaRetrieval (ar) revision: efa78cc2f74bbcd21eff2261f9e13aebe40b814e split: test type: jinaai/mintakaqa metrics:
    • type: main_score value: 22.778000000000002
    • type: map_at_1 value: 13.345
    • type: map_at_10 value: 19.336000000000002
    • type: map_at_100 value: 20.116999999999997
    • type: map_at_1000 value: 20.246
    • type: ndcg_at_1 value: 13.345
    • type: ndcg_at_10 value: 22.778000000000002
    • type: ndcg_at_100 value: 26.997
    • type: ndcg_at_1000 value: 31.564999999999998
    • type: ndcg_at_20 value: 24.368000000000002
    • type: ndcg_at_3 value: 18.622
    • type: ndcg_at_5 value: 20.72 task: type: Retrieval
  • dataset: config: arabic name: MTEB MrTidyRetrieval (arabic) revision: fc24a3ce8f09746410daee3d5cd823ff7a0675b7 split: test type: mteb/mrtidy metrics:
    • type: main_score value: 55.584999999999994
    • type: map_at_1 value: 34.197
    • type: map_at_10 value: 48.658
    • type: map_at_100 value: 49.491
    • type: map_at_1000 value: 49.518
    • type: ndcg_at_1 value: 36.91
    • type: ndcg_at_10 value: 55.584999999999994
    • type: ndcg_at_100 value: 59.082
    • type: ndcg_at_1000 value: 59.711000000000006
    • type: ndcg_at_20 value: 57.537000000000006
    • type: ndcg_at_3 value: 48.732
    • type: ndcg_at_5 value: 52.834 task: type: Retrieval
  • dataset: config: default name: MTEB SadeemQuestionRetrieval (default) revision: 3cb0752b182e5d5d740df547748b06663c8e0bd9 split: test type: sadeem-ai/sadeem-ar-eval-retrieval-questions metrics:
    • type: main_score value: 67.916
    • type: map_at_1 value: 31.785999999999998
    • type: map_at_10 value: 58.18600000000001
    • type: map_at_100 value: 58.287
    • type: map_at_1000 value: 58.29
    • type: ndcg_at_1 value: 31.785999999999998
    • type: ndcg_at_10 value: 67.916
    • type: ndcg_at_100 value: 68.44200000000001
    • type: ndcg_at_1000 value: 68.53399999999999
    • type: ndcg_at_20 value: 68.11
    • type: ndcg_at_3 value: 66.583
    • type: ndcg_at_5 value: 67.5 task: type: Retrieval
  • dataset: config: ara-ara name: MTEB XPQARetrieval (ara-ara) revision: c99d599f0a6ab9b85b065da6f9d94f9cf731679f split: test type: jinaai/xpqa metrics:
    • type: main_score value: 43.622
    • type: map_at_1 value: 19.236
    • type: map_at_10 value: 37.047000000000004
    • type: map_at_100 value: 38.948
    • type: map_at_1000 value: 39.054
    • type: ndcg_at_1 value: 35.333
    • type: ndcg_at_10 value: 43.622
    • type: ndcg_at_100 value: 50.761
    • type: ndcg_at_1000 value: 52.932
    • type: ndcg_at_20 value: 46.686
    • type: ndcg_at_3 value: 37.482
    • type: ndcg_at_5 value: 39.635999999999996 task: type: Retrieval tags:
• sentence-transformers
• sentence-similarity
• feature-extraction
• generated_from_trainer
• loss:MultipleNegativesRankingLoss
• retrieval
• mteb pipeline_tag: sentence-similarity library_name: sentence-transformers license: apache-2.0

🚀 Arabic-Retrieval-v1.0

这是一个高性能的阿拉伯语信息检索模型，基于强大的sentence-transformers框架构建，提供最先进的性能，并针对阿拉伯语的丰富性和复杂性进行了优化。

🔑 主要特点

• 🔥 卓越性能：与顶级多语言模型如e5-multilingual-large的准确性相当。详见评估
• 💡 专注于阿拉伯语：专门为阿拉伯语的细微差别和方言设计，确保更准确和上下文感知的结果。
• 📉 轻量高效：内存需求减少25%-50%，非常适合资源有限的环境或边缘部署。

🌍 为什么选择这个模型？

多语言模型功能强大，但它们通常体积庞大且未针对特定语言进行优化。这个模型弥补了这一差距，提供阿拉伯语原生能力，同时不牺牲性能或效率。无论您是在开发搜索引擎、聊天机器人还是大规模NLP管道，这个模型都能提供快速、准确且资源高效的解决方案。

模型详情

模型描述

• 模型类型：句子转换器
• 最大序列长度：512个标记
• 输出维度：768个标记
• 相似度函数：余弦相似度

完整模型架构

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, '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})