mteb 2.3.11__py3-none-any.whl → 2.4.2__py3-none-any.whl

mteb/models/model_implementations/mxbai_models.py

@@ -99,4 +99,10 @@ mxbai_embed_xsmall_v1 = ModelMeta(
     public_training_code=None,
     public_training_data=None,
     training_datasets=mixedbread_training_data,
+    citation="""@online{xsmall2024mxbai,
+  title={Every Byte Matters: Introducing mxbai-embed-xsmall-v1},
+  author={Sean Lee and Julius Lipp and Rui Huang and Darius Koenig},
+  year={2024},
+  url={https://www.mixedbread.ai/blog/mxbai-embed-xsmall-v1},
+}""",
 )

mteb/models/model_implementations/nomic_models.py

@@ -193,7 +193,7 @@ NOMIC_CITATION = """
 """
 
 nomic_embed_v1_5 = ModelMeta(
-    loader=NomicWrapper,
+    loader=NomicWrapper,  # type: ignore
     loader_kwargs=dict(
         trust_remote_code=True,
         model_prompts=model_prompts,
@@ -221,7 +221,7 @@ nomic_embed_v1_5 = ModelMeta(
 )
 
 nomic_embed_v1 = ModelMeta(
-    loader=NomicWrapper,
+    loader=NomicWrapper,  # type: ignore
     loader_kwargs=dict(
         trust_remote_code=True,
         model_prompts=model_prompts,
@@ -249,7 +249,7 @@ nomic_embed_v1 = ModelMeta(
 )
 
 nomic_embed_v1_ablated = ModelMeta(
-    loader=NomicWrapper,
+    loader=NomicWrapper,  # type: ignore
     loader_kwargs=dict(
         trust_remote_code=True,
         model_prompts=model_prompts,
@@ -276,7 +276,7 @@ nomic_embed_v1_ablated = ModelMeta(
 )
 
 nomic_embed_v1_unsupervised = ModelMeta(
-    loader=NomicWrapper,
+    loader=NomicWrapper,  # type: ignore
     loader_kwargs=dict(
         trust_remote_code=True,
         model_prompts=model_prompts,
@@ -328,4 +328,150 @@ nomic_modern_bert_embed = ModelMeta(
     superseded_by=None,
     training_datasets=nomic_training_data,
     public_training_data=None,
+    citation="""@misc{nussbaum2024nomic,
+      title={Nomic Embed: Training a Reproducible Long Context Text Embedder}, 
+      author={Zach Nussbaum and John X. Morris and Brandon Duderstadt and Andriy Mulyar},
+      year={2024},
+      eprint={2402.01613},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}""",
+)
+
+
+m_languages = [
+    "eng-Latn",
+    "spa-Latn",
+    "fra-Latn",
+    "deu-Latn",
+    "ita-Latn",
+    "por-Latn",
+    "pol-Latn",
+    "nld-Latn",
+    "tur-Latn",
+    "jpn-Jpan",
+    "vie-Latn",
+    "rus-Cyrl",
+    "ind-Latn",
+    "arb-Arab",
+    "ces-Latn",
+    "ron-Latn",
+    "swe-Latn",
+    "ell-Grek",
+    "ukr-Cyrl",
+    "zho-Hans",
+    "hun-Latn",
+    "dan-Latn",
+    "nor-Latn",
+    "hin-Deva",
+    "fin-Latn",
+    "bul-Cyrl",
+    "kor-Hang",
+    "slk-Latn",
+    "tha-Thai",
+    "heb-Hebr",
+    "cat-Latn",
+    "lit-Latn",
+    "fas-Arab",
+    "msa-Latn",
+    "slv-Latn",
+    "lav-Latn",
+    "mar-Deva",
+    "ben-Beng",
+    "sqi-Latn",
+    "cym-Latn",
+    "bel-Cyrl",
+    "mal-Mlym",
+    "kan-Knda",
+    "mkd-Cyrl",
+    "urd-Arab",
+    "fry-Latn",
+    "fil-Latn",
+    "tel-Telu",
+    "eus-Latn",
+    "swh-Latn",
+    "som-Latn",
+    "snd-Arab",
+    "uzb-Latn",
+    "cos-Latn",
+    "hrv-Latn",
+    "guj-Gujr",
+    "hin-Latn",
+    "ceb-Latn",
+    "epo-Latn",
+    "jav-Latn",
+    "lat-Latn",
+    "zul-Latn",
+    "mon-Cyrl",
+    "sin-Sinh",
+    "ell-Latn",
+    "gle-Latn",
+    "kir-Cyrl",
+    "tgk-Cyrl",
+    "mya-Mymr",
+    "khm-Khmr",
+    "mlg-Latn",
+    "pan-Guru",
+    "rus-Latn",
+    "sna-Latn",
+    "zho-Latn",
+    "hau-Latn",
+    "heb-Latn",
+    "hmn-Latn",
+    "hat-Latn",
+    "jpn-Latn",
+    "sun-Latn",
+    "bul-Latn",
+    "gla-Latn",
+    "nya-Latn",
+    "pus-Arab",
+    "kur-Latn",
+    "hbs-Latn",
+    "amh-Ethi",
+    "ibo-Latn",
+    "lao-Laoo",
+    "mri-Latn",
+    "nno-Latn",
+    "smo-Latn",
+    "yid-Hebr",
+    "sot-Latn",
+    "tgl-Latn",
+    "xho-Latn",
+    "yor-Latn",
+]
+
+nomic_embed_text_v2_moe = ModelMeta(
+    loader=NomicWrapper,  # type: ignore
+    loader_kwargs=dict(
+        trust_remote_code=True,
+        model_prompts=model_prompts,
+    ),
+    name="nomic-ai/nomic-embed-text-v2-moe",
+    languages=m_languages,
+    open_weights=True,
+    revision="1066b6599d099fbb93dfcb64f9c37a7c9e503e85",
+    release_date="2025-02-07",
+    n_parameters=475292928,
+    memory_usage_mb=1813,
+    max_tokens=512,
+    embed_dim=768,
+    license="apache-2.0",
+    reference="https://huggingface.co/nomic-ai/nomic-embed-text-v2-moe",
+    similarity_fn_name=ScoringFunction.COSINE,
+    framework=["Sentence Transformers", "PyTorch"],
+    use_instructions=True,
+    adapted_from="nomic-ai/nomic-xlm-2048",
+    public_training_data="https://github.com/nomic-ai/contrastors?tab=readme-ov-file#data-access",
+    public_training_code="https://github.com/nomic-ai/contrastors/blob/613ddfd37309e538cceadb05b1e6423e7b09f603/src/contrastors/configs/train/contrastive_finetune_moe.yaml",
+    training_datasets=None,  # did not look into this further
+    superseded_by=None,
+    citation="""@misc{nussbaum2025trainingsparsemixtureexperts,
+      title={Training Sparse Mixture Of Experts Text Embedding Models}, 
+      author={Zach Nussbaum and Brandon Duderstadt},
+      year={2025},
+      eprint={2502.07972},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2502.07972}, 
+}""",
 )

mteb/models/model_implementations/pylate_models.py

@@ -415,6 +415,30 @@ jina_colbert_v2 = ModelMeta(
         "DuRetrieval",
         "MIRACL",
     },
+    citation="""@inproceedings{xiao-etal-2024-jina,
+    title = "{J}ina-{C}ol{BERT}-v2: A General-Purpose Multilingual Late Interaction Retriever",
+    author = {Jha, Rohan  and
+      Wang, Bo  and
+      G{\"u}nther, Michael  and
+      Mastrapas, Georgios  and
+      Sturua, Saba  and
+      Mohr, Isabelle  and
+      Koukounas, Andreas  and
+      Wang, Mohammad Kalim  and
+      Wang, Nan  and
+      Xiao, Han},
+    editor = {S{\"a}lev{\"a}, Jonne  and
+      Owodunni, Abraham},
+    booktitle = "Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024)",
+    month = nov,
+    year = "2024",
+    address = "Miami, Florida, USA",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2024.mrl-1.11/",
+    doi = "10.18653/v1/2024.mrl-1.11",
+    pages = "159--166",
+    abstract = "Multi-vector dense models, such as ColBERT, have proven highly effective in information retrieval. ColBERT`s late interaction scoring approximates the joint query-document attention seen in cross-encoders while maintaining inference efficiency closer to traditional dense retrieval models, thanks to its bi-encoder architecture and recent optimizations in indexing and search. In this paper, we introduce a novel architecture and a training framework to support long context window and multilingual retrieval. Leveraging Matryoshka Representation Loss, we further demonstrate that the reducing the embedding dimensionality from 128 to 64 has insignificant impact on the model`s retrieval performance and cut storage requirements by up to 50{\%}. Our new model, Jina-ColBERT-v2, demonstrates strong performance across a range of English and multilingual retrieval tasks,"
+}""",
 )
 
 
@@ -444,4 +468,13 @@ lightonai__gte_moderncolbert_v1 = ModelMeta(
         "MSMARCO",
         "mMARCO-NL",
     },
+    citation="""@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"
+}""",
 )

mteb/models/model_implementations/ru_sentence_models.py

@@ -439,6 +439,13 @@ user_bge_m3 = ModelMeta(
     },
     public_training_code=None,
     public_training_data=None,
+    citation="""@misc{deepvk2024user,
+    title={USER: Universal Sentence Encoder for Russian},
+    author={Malashenko, Boris and  Zemerov, Anton and Spirin, Egor},
+    url={https://huggingface.co/datasets/deepvk/USER-base},
+    publisher={Hugging Face},
+    year={2024},
+}""",
 )
 
 deberta_v1_ru = ModelMeta(
@@ -873,6 +880,7 @@ frida = ModelMeta(
     public_training_data=None,
     public_training_code=None,
     framework=["Sentence Transformers", "PyTorch"],
+    citation=None,
 )
 
 giga_embeddings = ModelMeta(
@@ -1008,6 +1016,13 @@ user2_small = ModelMeta(
     public_training_data=None,
     public_training_code="https://github.com/BlessedTatonka/some_code/tree/2899f27d51efdf4217fc6453799ff197e9792f1e",
     framework=["Sentence Transformers", "PyTorch"],
+    citation="""@misc{deepvk2025user,
+    title={USER2},
+    author={Malashenko, Boris and Spirin, Egor and Sokolov Andrey},
+    url={https://huggingface.co/deepvk/USER2-small},
+    publisher={Hugging Face},
+    year={2025},
+}""",
 )
 
 user2_base = ModelMeta(
@@ -1033,4 +1048,11 @@ user2_base = ModelMeta(
     public_training_data=None,
     public_training_code="https://github.com/BlessedTatonka/some_code/tree/2899f27d51efdf4217fc6453799ff197e9792f1e",
     framework=["Sentence Transformers", "PyTorch"],
+    citation="""@misc{deepvk2025user,
+    title={USER2},
+    author={Malashenko, Boris and Spirin, Egor and Sokolov Andrey},
+    url={https://huggingface.co/deepvk/USER2-base},
+    publisher={Hugging Face},
+    year={2025},
+}""",
 )

mteb/models/model_implementations/sentence_transformers_models.py

@@ -402,6 +402,15 @@ static_similarity_mrl_multilingual_v1 = ModelMeta(
     training_datasets=static_multi_datasets,
     public_training_code="https://huggingface.co/blog/static-embeddings",
     public_training_data="https://huggingface.co/collections/sentence-transformers/embedding-model-datasets-6644d7a3673a511914aa7552",
+    citation="""@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",
+}""",
 )
 
 contriever = ModelMeta(
@@ -467,6 +476,17 @@ microllama_text_embedding = ModelMeta(
     public_training_data=None,
 )
 
+SENTENCE_T5_CITATION = """
+@misc{ni2021sentencet5scalablesentenceencoders,
+      title={Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models}, 
+      author={Jianmo Ni and Gustavo Hernández Ábrego and Noah Constant and Ji Ma and Keith B. Hall and Daniel Cer and Yinfei Yang},
+      year={2021},
+      eprint={2108.08877},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2108.08877}, 
+}
+"""
 sentence_t5_base = ModelMeta(
     loader=sentence_transformers_loader,
     name="sentence-transformers/sentence-t5-base",
@@ -486,6 +506,7 @@ sentence_t5_base = ModelMeta(
     public_training_code=None,
     public_training_data=None,
     training_datasets={"SNLI", "Community QA"},
+    citation=SENTENCE_T5_CITATION,
 )
 
 sentence_t5_large = ModelMeta(
@@ -507,6 +528,7 @@ sentence_t5_large = ModelMeta(
     public_training_code=None,
     public_training_data=None,
     training_datasets={"SNLI", "Community QA"},
+    citation=SENTENCE_T5_CITATION,
 )
 
 sentence_t5_xl = ModelMeta(
@@ -528,6 +550,7 @@ sentence_t5_xl = ModelMeta(
     public_training_code=None,
     public_training_data=None,
     training_datasets={"SNLI", "Community QA"},
+    citation=SENTENCE_T5_CITATION,
 )
 
 sentence_t5_xxl = ModelMeta(
@@ -549,7 +572,19 @@ sentence_t5_xxl = ModelMeta(
     public_training_code=None,
     public_training_data=None,
     training_datasets={"SNLI", "Community QA"},
+    citation=SENTENCE_T5_CITATION,
 )
+GTR_CITATION = """
+@misc{ni2021largedualencodersgeneralizable,
+      title={Large Dual Encoders Are Generalizable Retrievers}, 
+      author={Jianmo Ni and Chen Qu and Jing Lu and Zhuyun Dai and Gustavo Hernández Ábrego and Ji Ma and Vincent Y. Zhao and Yi Luan and Keith B. Hall and Ming-Wei Chang and Yinfei Yang},
+      year={2021},
+      eprint={2112.07899},
+      archivePrefix={arXiv},
+      primaryClass={cs.IR},
+      url={https://arxiv.org/abs/2112.07899}, 
+}
+"""
 gtr_t5_large = ModelMeta(
     loader=sentence_transformers_loader,
     name="sentence-transformers/gtr-t5-large",
@@ -581,6 +616,7 @@ gtr_t5_large = ModelMeta(
         "NQ-PL",  # translation not trained on
         "Community QA",
     },
+    citation=GTR_CITATION,
 )
 
 gtr_t5_xl = ModelMeta(
@@ -614,6 +650,7 @@ gtr_t5_xl = ModelMeta(
         "NQ-PL",  # translation not trained on
         "Community QA",
     },
+    citation=GTR_CITATION,
 )
 gtr_t5_xxl = ModelMeta(
     loader=sentence_transformers_loader,
@@ -646,6 +683,7 @@ gtr_t5_xxl = ModelMeta(
         "NQ-PL",  # translation not trained on
         "Community QA",
     },
+    citation=GTR_CITATION,
 )
 
 gtr_t5_base = ModelMeta(
@@ -679,4 +717,5 @@ gtr_t5_base = ModelMeta(
         "NQ-PL",  # translation not trained on
         "Community QA",
     },
+    citation=GTR_CITATION,
 )

mteb/models/model_implementations/spartan8806_atles_champion.py

@@ -23,4 +23,11 @@ spartan8806_atles_champion_embedding = ModelMeta(
     adapted_from="sentence-transformers/all-mpnet-base-v2",
     public_training_code=None,
     public_training_data=None,
+    citation="""@article{conner2025epistemic,
+  title={The Epistemic Barrier: How RLHF Makes AI Consciousness Empirically Undecidable},
+  author={Conner (spartan8806)},
+  journal={ATLES Research Papers},
+  year={2025},
+  note={Cross-model validation study (Phoenix, Grok, Gemini, Claude)}
+}""",
 )

mteb/models/model_implementations/ua_sentence_models.py

@@ -28,4 +28,13 @@ xlm_roberta_ua_distilled = ModelMeta(
     modalities=["text"],
     public_training_data=None,
     use_instructions=False,
+    citation="""@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",
+}""",
 )

mteb/models/model_implementations/vi_vn_models.py

@@ -75,6 +75,12 @@ aiteamvn_vietnamese_embeddings = ModelMeta(
     public_training_data=None,
     training_datasets=None,
     adapted_from="BAAI/bge-m3",
+    citation="""@misc{Vietnamese_Embedding,
+  title={Vietnamese_Embedding: Embedding model in Vietnamese language.},
+  author={Nguyen Nho Trung, Nguyen Nhat Quang, Nguyen Van Huy},
+  year={2025},
+  publisher={Huggingface},
+}""",
 )
 
 hiieu_halong_embedding = ModelMeta(
@@ -99,6 +105,12 @@ hiieu_halong_embedding = ModelMeta(
     public_training_data=None,
     training_datasets=None,
     adapted_from="intfloat/multilingual-e5-base",
+    citation="""@misc{HalongEmbedding,
+  title={HalongEmbedding: A Vietnamese Text Embedding},
+  author={Ngo Hieu},
+  year={2024},
+  publisher={Huggingface},
+}""",
 )
 
 sup_simcse_vietnamese_phobert_base_ = ModelMeta(
@@ -122,6 +134,20 @@ sup_simcse_vietnamese_phobert_base_ = ModelMeta(
     reference="https://huggingface.co/VoVanPhuc/sup-SimCSE-VietNamese-phobert-base",
     similarity_fn_name="cosine",
     training_datasets=None,
+    citation="""@article{gao2021simcse,
+   title={{SimCSE}: Simple Contrastive Learning of Sentence Embeddings},
+   author={Gao, Tianyu and Yao, Xingcheng and Chen, Danqi},
+   journal={arXiv preprint arXiv:2104.08821},
+   year={2021}
+}
+
+@inproceedings{phobert,
+title     = {{PhoBERT: Pre-trained language models for Vietnamese}},
+author    = {Dat Quoc Nguyen and Anh Tuan Nguyen},
+booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2020},
+year      = {2020},
+pages     = {1037--1042}
+}""",
 )
 
 bkai_foundation_models_vietnamese_bi_encoder = ModelMeta(
@@ -145,4 +171,11 @@ bkai_foundation_models_vietnamese_bi_encoder = ModelMeta(
     reference="https://huggingface.co/bkai-foundation-models/vietnamese-bi-encoder",
     similarity_fn_name="cosine",
     training_datasets=None,
+    citation="""
+      @article{duc2024towards,
+    title={Towards Comprehensive Vietnamese Retrieval-Augmented Generation and Large Language Models},
+    author={Nguyen Quang Duc, Le Hai Son, Nguyen Duc Nhan, Nguyen Dich Nhat Minh, Le Thanh Huong, Dinh Viet Sang},
+    journal={arXiv preprint arXiv:2403.01616},
+    year={2024}
+  }""",
 )