mteb 2.6.4__py3-none-any.whl → 2.6.5__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (126) hide show
  1. mteb/abstasks/classification.py +2 -3
  2. mteb/abstasks/multilabel_classification.py +3 -3
  3. mteb/abstasks/regression.py +1 -1
  4. mteb/abstasks/retrieval.py +1 -1
  5. mteb/abstasks/task_metadata.py +9 -14
  6. mteb/models/model_implementations/align_models.py +1 -1
  7. mteb/models/model_implementations/andersborges.py +2 -2
  8. mteb/models/model_implementations/ara_models.py +1 -1
  9. mteb/models/model_implementations/arctic_models.py +8 -8
  10. mteb/models/model_implementations/b1ade_models.py +1 -1
  11. mteb/models/model_implementations/bge_models.py +45 -21
  12. mteb/models/model_implementations/bica_model.py +3 -3
  13. mteb/models/model_implementations/blip2_models.py +2 -2
  14. mteb/models/model_implementations/blip_models.py +8 -8
  15. mteb/models/model_implementations/bmretriever_models.py +4 -4
  16. mteb/models/model_implementations/cadet_models.py +1 -1
  17. mteb/models/model_implementations/cde_models.py +2 -2
  18. mteb/models/model_implementations/clip_models.py +3 -3
  19. mteb/models/model_implementations/clips_models.py +3 -3
  20. mteb/models/model_implementations/codefuse_models.py +5 -5
  21. mteb/models/model_implementations/codesage_models.py +3 -3
  22. mteb/models/model_implementations/cohere_models.py +4 -4
  23. mteb/models/model_implementations/colpali_models.py +3 -3
  24. mteb/models/model_implementations/colqwen_models.py +8 -8
  25. mteb/models/model_implementations/colsmol_models.py +2 -2
  26. mteb/models/model_implementations/conan_models.py +1 -1
  27. mteb/models/model_implementations/dino_models.py +19 -19
  28. mteb/models/model_implementations/e5_instruct.py +23 -4
  29. mteb/models/model_implementations/e5_models.py +9 -9
  30. mteb/models/model_implementations/e5_v.py +1 -1
  31. mteb/models/model_implementations/eagerworks_models.py +1 -1
  32. mteb/models/model_implementations/emillykkejensen_models.py +3 -3
  33. mteb/models/model_implementations/en_code_retriever.py +1 -1
  34. mteb/models/model_implementations/euler_models.py +2 -2
  35. mteb/models/model_implementations/fa_models.py +9 -9
  36. mteb/models/model_implementations/facebookai.py +14 -2
  37. mteb/models/model_implementations/geogpt_models.py +1 -1
  38. mteb/models/model_implementations/gme_v_models.py +2 -2
  39. mteb/models/model_implementations/google_models.py +1 -1
  40. mteb/models/model_implementations/granite_vision_embedding_models.py +1 -1
  41. mteb/models/model_implementations/gritlm_models.py +2 -2
  42. mteb/models/model_implementations/gte_models.py +25 -13
  43. mteb/models/model_implementations/hinvec_models.py +1 -1
  44. mteb/models/model_implementations/ibm_granite_models.py +30 -6
  45. mteb/models/model_implementations/inf_models.py +2 -2
  46. mteb/models/model_implementations/jasper_models.py +2 -2
  47. mteb/models/model_implementations/jina_clip.py +1 -1
  48. mteb/models/model_implementations/jina_models.py +11 -5
  49. mteb/models/model_implementations/kblab.py +12 -6
  50. mteb/models/model_implementations/kennethenevoldsen_models.py +2 -2
  51. mteb/models/model_implementations/kfst.py +1 -1
  52. mteb/models/model_implementations/kowshik24_models.py +1 -1
  53. mteb/models/model_implementations/lgai_embedding_models.py +1 -1
  54. mteb/models/model_implementations/linq_models.py +1 -1
  55. mteb/models/model_implementations/listconranker.py +1 -1
  56. mteb/models/model_implementations/llm2clip_models.py +3 -3
  57. mteb/models/model_implementations/llm2vec_models.py +8 -8
  58. mteb/models/model_implementations/mdbr_models.py +14 -2
  59. mteb/models/model_implementations/misc_models.py +68 -68
  60. mteb/models/model_implementations/mme5_models.py +1 -1
  61. mteb/models/model_implementations/moco_models.py +2 -2
  62. mteb/models/model_implementations/mod_models.py +1 -1
  63. mteb/models/model_implementations/model2vec_models.py +13 -13
  64. mteb/models/model_implementations/moka_models.py +1 -1
  65. mteb/models/model_implementations/mxbai_models.py +16 -3
  66. mteb/models/model_implementations/nbailab.py +3 -3
  67. mteb/models/model_implementations/no_instruct_sentence_models.py +1 -1
  68. mteb/models/model_implementations/nomic_models.py +18 -6
  69. mteb/models/model_implementations/nomic_models_vision.py +1 -1
  70. mteb/models/model_implementations/nvidia_llama_nemoretriever_colemb.py +2 -2
  71. mteb/models/model_implementations/nvidia_models.py +3 -3
  72. mteb/models/model_implementations/octen_models.py +2 -2
  73. mteb/models/model_implementations/openclip_models.py +6 -6
  74. mteb/models/model_implementations/opensearch_neural_sparse_models.py +5 -5
  75. mteb/models/model_implementations/ops_moa_models.py +1 -1
  76. mteb/models/model_implementations/ordalietech_solon_embeddings_mini_beta_1_1.py +1 -1
  77. mteb/models/model_implementations/pawan_models.py +1 -1
  78. mteb/models/model_implementations/piccolo_models.py +1 -1
  79. mteb/models/model_implementations/promptriever_models.py +4 -4
  80. mteb/models/model_implementations/pylate_models.py +5 -5
  81. mteb/models/model_implementations/qodo_models.py +2 -2
  82. mteb/models/model_implementations/qtack_models.py +1 -1
  83. mteb/models/model_implementations/qwen3_models.py +3 -3
  84. mteb/models/model_implementations/qzhou_models.py +2 -2
  85. mteb/models/model_implementations/rasgaard_models.py +1 -1
  86. mteb/models/model_implementations/reasonir_model.py +1 -1
  87. mteb/models/model_implementations/repllama_models.py +1 -1
  88. mteb/models/model_implementations/rerankers_custom.py +9 -3
  89. mteb/models/model_implementations/rerankers_monot5_based.py +14 -14
  90. mteb/models/model_implementations/richinfoai_models.py +1 -1
  91. mteb/models/model_implementations/ru_sentence_models.py +20 -20
  92. mteb/models/model_implementations/ruri_models.py +10 -10
  93. mteb/models/model_implementations/salesforce_models.py +3 -3
  94. mteb/models/model_implementations/samilpwc_models.py +1 -1
  95. mteb/models/model_implementations/sarashina_embedding_models.py +2 -2
  96. mteb/models/model_implementations/searchmap_models.py +1 -1
  97. mteb/models/model_implementations/sentence_transformers_models.py +58 -22
  98. mteb/models/model_implementations/shuu_model.py +1 -1
  99. mteb/models/model_implementations/siglip_models.py +10 -10
  100. mteb/models/model_implementations/slm_models.py +416 -0
  101. mteb/models/model_implementations/spartan8806_atles_champion.py +1 -1
  102. mteb/models/model_implementations/stella_models.py +17 -4
  103. mteb/models/model_implementations/tarka_models.py +2 -2
  104. mteb/models/model_implementations/text2vec_models.py +9 -3
  105. mteb/models/model_implementations/ua_sentence_models.py +1 -1
  106. mteb/models/model_implementations/uae_models.py +7 -1
  107. mteb/models/model_implementations/vdr_models.py +1 -1
  108. mteb/models/model_implementations/vi_vn_models.py +6 -6
  109. mteb/models/model_implementations/vlm2vec_models.py +2 -2
  110. mteb/models/model_implementations/youtu_models.py +1 -1
  111. mteb/models/model_implementations/yuan_models.py +1 -1
  112. mteb/models/model_implementations/yuan_models_en.py +1 -1
  113. mteb/models/model_meta.py +46 -17
  114. mteb/results/benchmark_results.py +2 -2
  115. mteb/tasks/classification/kur/kurdish_sentiment_classification.py +2 -2
  116. mteb/tasks/clustering/eng/hume_wiki_cities_clustering.py +1 -1
  117. mteb/tasks/clustering/eng/wiki_cities_clustering.py +1 -1
  118. mteb/tasks/clustering/zho/cmteb_clustering.py +2 -2
  119. mteb/tasks/reranking/multilingual/wikipedia_reranking_multilingual.py +1 -1
  120. mteb/tasks/retrieval/eng/cub200_i2i_retrieval.py +1 -1
  121. {mteb-2.6.4.dist-info → mteb-2.6.5.dist-info}/METADATA +3 -1
  122. {mteb-2.6.4.dist-info → mteb-2.6.5.dist-info}/RECORD +126 -125
  123. {mteb-2.6.4.dist-info → mteb-2.6.5.dist-info}/WHEEL +0 -0
  124. {mteb-2.6.4.dist-info → mteb-2.6.5.dist-info}/entry_points.txt +0 -0
  125. {mteb-2.6.4.dist-info → mteb-2.6.5.dist-info}/licenses/LICENSE +0 -0
  126. {mteb-2.6.4.dist-info → mteb-2.6.5.dist-info}/top_level.txt +0 -0
@@ -17,7 +17,7 @@ potion_base_8m = ModelMeta(
17
17
  embed_dim=256,
18
18
  license="mit",
19
19
  similarity_fn_name=ScoringFunction.COSINE,
20
- framework=["NumPy", "Sentence Transformers"],
20
+ framework=["NumPy", "Sentence Transformers", "safetensors"],
21
21
  reference="https://huggingface.co/rasgaard/m2v-dfm-large",
22
22
  use_instructions=False,
23
23
  adapted_from="KennethEnevoldsen/dfm-sentence-encoder-large",
@@ -56,7 +56,7 @@ ReasonIR_8B = ModelMeta(
56
56
  max_tokens=131072,
57
57
  reference="https://huggingface.co/ReasonIR/ReasonIR-8B",
58
58
  similarity_fn_name="cosine",
59
- framework=["Sentence Transformers", "PyTorch"],
59
+ framework=["Sentence Transformers", "PyTorch", "Transformers", "safetensors"],
60
60
  use_instructions=True,
61
61
  training_datasets=REASONIR_TRAINING_DATA,
62
62
  public_training_code="https://github.com/facebookresearch/ReasonIR/tree/main/training",
@@ -207,7 +207,7 @@ repllama_llama2_reproduced = ModelMeta(
207
207
  license="apache-2.0",
208
208
  reference="https://huggingface.co/samaya-ai/RepLLaMA-reproduced",
209
209
  similarity_fn_name=ScoringFunction.COSINE,
210
- framework=["PyTorch", "Tevatron"],
210
+ framework=["PyTorch", "Tevatron", "safetensors"],
211
211
  use_instructions=True,
212
212
  citation=REPLLAMA_CITATION,
213
213
  public_training_code=None,
@@ -234,7 +234,7 @@ monobert_large = ModelMeta(
234
234
  similarity_fn_name=None,
235
235
  use_instructions=None,
236
236
  training_datasets=None,
237
- framework=["Sentence Transformers", "PyTorch"],
237
+ framework=["Sentence Transformers", "PyTorch", "Transformers"],
238
238
  )
239
239
 
240
240
  # languages unclear: https://huggingface.co/jinaai/jina-reranker-v2-base-multilingual/discussions/28
@@ -259,7 +259,13 @@ jina_reranker_multilingual = ModelMeta(
259
259
  similarity_fn_name=None,
260
260
  use_instructions=None,
261
261
  training_datasets=None,
262
- framework=["Sentence Transformers", "PyTorch"],
262
+ framework=[
263
+ "Sentence Transformers",
264
+ "PyTorch",
265
+ "Transformers",
266
+ "ONNX",
267
+ "safetensors",
268
+ ],
263
269
  )
264
270
 
265
271
  bge_reranker_v2_m3 = ModelMeta(
@@ -316,7 +322,7 @@ bge_reranker_v2_m3 = ModelMeta(
316
322
  similarity_fn_name=None,
317
323
  use_instructions=None,
318
324
  training_datasets=bge_m3_training_data,
319
- framework=["Sentence Transformers", "PyTorch"],
325
+ framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
320
326
  citation="""
321
327
  @misc{li2023making,
322
328
  title={Making Large Language Models A Better Foundation For Dense Retrieval},
@@ -330,7 +330,7 @@ monot5_small = ModelMeta(
330
330
  similarity_fn_name=None,
331
331
  use_instructions=None,
332
332
  training_datasets=None,
333
- framework=["PyTorch"],
333
+ framework=["PyTorch", "Transformers"],
334
334
  citation="""@misc{rosa2022parameterleftbehinddistillation,
335
335
  title={No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval},
336
336
  author={Guilherme Moraes Rosa and Luiz Bonifacio and Vitor Jeronymo and Hugo Abonizio and Marzieh Fadaee and Roberto Lotufo and Rodrigo Nogueira},
@@ -372,7 +372,7 @@ monot5_base = ModelMeta(
372
372
  similarity_fn_name=None,
373
373
  use_instructions=None,
374
374
  training_datasets=None,
375
- framework=["PyTorch"],
375
+ framework=["PyTorch", "Transformers"],
376
376
  )
377
377
 
378
378
  monot5_large = ModelMeta(
@@ -396,7 +396,7 @@ monot5_large = ModelMeta(
396
396
  similarity_fn_name=None,
397
397
  use_instructions=None,
398
398
  training_datasets=None,
399
- framework=["PyTorch"],
399
+ framework=["PyTorch", "Transformers"],
400
400
  citation="""@misc{rosa2022parameterleftbehinddistillation,
401
401
  title={No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval},
402
402
  author={Guilherme Moraes Rosa and Luiz Bonifacio and Vitor Jeronymo and Hugo Abonizio and Marzieh Fadaee and Roberto Lotufo and Rodrigo Nogueira},
@@ -429,7 +429,7 @@ monot5_3b = ModelMeta(
429
429
  similarity_fn_name=None,
430
430
  use_instructions=None,
431
431
  training_datasets=None,
432
- framework=["PyTorch"],
432
+ framework=["PyTorch", "Transformers"],
433
433
  citation="""@misc{rosa2022parameterleftbehinddistillation,
434
434
  title={No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval},
435
435
  author={Guilherme Moraes Rosa and Luiz Bonifacio and Vitor Jeronymo and Hugo Abonizio and Marzieh Fadaee and Roberto Lotufo and Rodrigo Nogueira},
@@ -484,7 +484,7 @@ flant5_base = ModelMeta(
484
484
  public_training_data=None,
485
485
  similarity_fn_name=None,
486
486
  use_instructions=None,
487
- framework=["PyTorch"],
487
+ framework=["PyTorch", "Transformers", "safetensors"],
488
488
  )
489
489
 
490
490
  flant5_large = ModelMeta(
@@ -530,7 +530,7 @@ flant5_large = ModelMeta(
530
530
  public_training_data=None,
531
531
  similarity_fn_name=None,
532
532
  use_instructions=None,
533
- framework=["PyTorch"],
533
+ framework=["PyTorch", "Transformers", "safetensors"],
534
534
  )
535
535
 
536
536
  flant5_xl = ModelMeta(
@@ -576,7 +576,7 @@ flant5_xl = ModelMeta(
576
576
  public_training_data=None,
577
577
  similarity_fn_name=None,
578
578
  use_instructions=None,
579
- framework=["PyTorch"],
579
+ framework=["PyTorch", "Transformers", "safetensors"],
580
580
  )
581
581
 
582
582
  flant5_xxl = ModelMeta(
@@ -622,7 +622,7 @@ flant5_xxl = ModelMeta(
622
622
  public_training_data=None,
623
623
  similarity_fn_name=None,
624
624
  use_instructions=None,
625
- framework=["PyTorch"],
625
+ framework=["PyTorch", "Transformers", "safetensors"],
626
626
  )
627
627
 
628
628
 
@@ -647,7 +647,7 @@ llama2_7b = ModelMeta(
647
647
  similarity_fn_name=None,
648
648
  use_instructions=None,
649
649
  training_datasets=None,
650
- framework=["PyTorch"],
650
+ framework=["PyTorch", "Transformers", "safetensors"],
651
651
  citation="""@misc{touvron2023llama2openfoundation,
652
652
  title={Llama 2: Open Foundation and Fine-Tuned Chat Models},
653
653
  author={Hugo Touvron and Louis Martin and Kevin Stone and Peter Albert and Amjad Almahairi and Yasmine Babaei and Nikolay Bashlykov and Soumya Batra and Prajjwal Bhargava and Shruti Bhosale and Dan Bikel and Lukas Blecher and Cristian Canton Ferrer and Moya Chen and Guillem Cucurull and David Esiobu and Jude Fernandes and Jeremy Fu and Wenyin Fu and Brian Fuller and Cynthia Gao and Vedanuj Goswami and Naman Goyal and Anthony Hartshorn and Saghar Hosseini and Rui Hou and Hakan Inan and Marcin Kardas and Viktor Kerkez and Madian Khabsa and Isabel Kloumann and Artem Korenev and Punit Singh Koura and Marie-Anne Lachaux and Thibaut Lavril and Jenya Lee and Diana Liskovich and Yinghai Lu and Yuning Mao and Xavier Martinet and Todor Mihaylov and Pushkar Mishra and Igor Molybog and Yixin Nie and Andrew Poulton and Jeremy Reizenstein and Rashi Rungta and Kalyan Saladi and Alan Schelten and Ruan Silva and Eric Michael Smith and Ranjan Subramanian and Xiaoqing Ellen Tan and Binh Tang and Ross Taylor and Adina Williams and Jian Xiang Kuan and Puxin Xu and Zheng Yan and Iliyan Zarov and Yuchen Zhang and Angela Fan and Melanie Kambadur and Sharan Narang and Aurelien Rodriguez and Robert Stojnic and Sergey Edunov and Thomas Scialom},
@@ -689,7 +689,7 @@ llama2_7b_chat = ModelMeta(
689
689
  similarity_fn_name=None,
690
690
  use_instructions=None,
691
691
  training_datasets=None,
692
- framework=["PyTorch"],
692
+ framework=["PyTorch", "Transformers", "safetensors"],
693
693
  )
694
694
 
695
695
  mistral_7b = ModelMeta(
@@ -713,7 +713,7 @@ mistral_7b = ModelMeta(
713
713
  similarity_fn_name=None,
714
714
  use_instructions=None,
715
715
  training_datasets=None,
716
- framework=["PyTorch"],
716
+ framework=["PyTorch", "Transformers", "safetensors"],
717
717
  citation="""@misc{jiang2023mistral7b,
718
718
  title={Mistral 7B},
719
719
  author={Albert Q. Jiang and Alexandre Sablayrolles and Arthur Mensch and Chris Bamford and Devendra Singh Chaplot and Diego de las Casas and Florian Bressand and Gianna Lengyel and Guillaume Lample and Lucile Saulnier and Lélio Renard Lavaud and Marie-Anne Lachaux and Pierre Stock and Teven Le Scao and Thibaut Lavril and Thomas Wang and Timothée Lacroix and William El Sayed},
@@ -748,7 +748,7 @@ followir_7b = ModelMeta(
748
748
  public_training_data=None,
749
749
  similarity_fn_name=None,
750
750
  use_instructions=None,
751
- framework=["PyTorch"],
751
+ framework=["PyTorch", "Transformers", "safetensors"],
752
752
  citation="""
753
753
  @misc{weller2024followir,
754
754
  title={FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions},
@@ -898,7 +898,7 @@ mt5_base_mmarco_v2 = ModelMeta(
898
898
  public_training_data=None,
899
899
  similarity_fn_name=None,
900
900
  use_instructions=None,
901
- framework=["PyTorch"],
901
+ framework=["PyTorch", "Transformers"],
902
902
  )
903
903
 
904
904
  mt5_13b_mmarco_100k = ModelMeta(
@@ -922,5 +922,5 @@ mt5_13b_mmarco_100k = ModelMeta(
922
922
  similarity_fn_name=None,
923
923
  use_instructions=None,
924
924
  training_datasets=None,
925
- framework=["PyTorch"],
925
+ framework=["PyTorch", "Transformers"],
926
926
  )
@@ -21,7 +21,7 @@ ritrieve_zh_v1 = ModelMeta(
21
21
  max_tokens=512,
22
22
  reference="https://huggingface.co/richinfoai/ritrieve_zh_v1",
23
23
  similarity_fn_name="cosine",
24
- framework=["Sentence Transformers", "PyTorch"],
24
+ framework=["Sentence Transformers", "PyTorch", "safetensors"],
25
25
  use_instructions=False,
26
26
  superseded_by=None,
27
27
  adapted_from=None,
@@ -250,7 +250,7 @@ rubert_tiny = ModelMeta(
250
250
  max_tokens=512,
251
251
  reference="https://huggingface.co/cointegrated/rubert-tiny",
252
252
  similarity_fn_name=ScoringFunction.COSINE,
253
- framework=["Sentence Transformers", "PyTorch"],
253
+ framework=["Sentence Transformers", "PyTorch", "Transformers", "safetensors"],
254
254
  use_instructions=False,
255
255
  public_training_code="https://gist.github.com/avidale/7bc6350f26196918bf339c01261f5c60",
256
256
  training_datasets={
@@ -276,7 +276,7 @@ rubert_tiny2 = ModelMeta(
276
276
  max_tokens=2048,
277
277
  reference="https://huggingface.co/cointegrated/rubert-tiny2",
278
278
  similarity_fn_name=ScoringFunction.COSINE,
279
- framework=["Sentence Transformers", "PyTorch"],
279
+ framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
280
280
  use_instructions=False,
281
281
  public_training_code="https://colab.research.google.com/drive/1mSWfIQ6PIlteLVZ9DKKpcorycgLIKZLf?usp=sharing",
282
282
  training_datasets=set(
@@ -303,7 +303,7 @@ sbert_large_nlu_ru = ModelMeta(
303
303
  max_tokens=512, # best guess
304
304
  reference="https://huggingface.co/ai-forever/sbert_large_nlu_ru",
305
305
  similarity_fn_name=ScoringFunction.COSINE,
306
- framework=["Sentence Transformers", "PyTorch"],
306
+ framework=["Sentence Transformers", "PyTorch", "Transformers", "safetensors"],
307
307
  use_instructions=False,
308
308
  public_training_code=None,
309
309
  public_training_data=None,
@@ -329,7 +329,7 @@ sbert_large_mt_nlu_ru = ModelMeta(
329
329
  max_tokens=512, # best guess
330
330
  reference="https://huggingface.co/ai-forever/sbert_large_mt_nlu_ru",
331
331
  similarity_fn_name=ScoringFunction.COSINE,
332
- framework=["Sentence Transformers", "PyTorch"],
332
+ framework=["Sentence Transformers", "PyTorch", "Transformers", "safetensors"],
333
333
  use_instructions=False,
334
334
  public_training_code=None,
335
335
  public_training_data=None,
@@ -357,7 +357,7 @@ user_base_ru = ModelMeta(
357
357
  max_tokens=512,
358
358
  reference="https://huggingface.co/deepvk/USER-base",
359
359
  similarity_fn_name=ScoringFunction.COSINE,
360
- framework=["Sentence Transformers", "PyTorch"],
360
+ framework=["Sentence Transformers", "PyTorch", "safetensors"],
361
361
  adapted_from="https://huggingface.co/deepvk/deberta-v1-base",
362
362
  use_instructions=True,
363
363
  citation="""@misc{deepvk2024user,
@@ -418,7 +418,7 @@ user_bge_m3 = ModelMeta(
418
418
  max_tokens=8194,
419
419
  reference="https://huggingface.co/deepvk/USER-base",
420
420
  similarity_fn_name=ScoringFunction.COSINE,
421
- framework=["Sentence Transformers", "PyTorch"],
421
+ framework=["Sentence Transformers", "PyTorch", "safetensors"],
422
422
  adapted_from="BAAI/bge-m3",
423
423
  use_instructions=False,
424
424
  training_datasets={
@@ -469,7 +469,7 @@ deberta_v1_ru = ModelMeta(
469
469
  max_tokens=512,
470
470
  reference="https://huggingface.co/deepvk/deberta-v1-base",
471
471
  similarity_fn_name=ScoringFunction.COSINE,
472
- framework=["Sentence Transformers", "PyTorch"],
472
+ framework=["Sentence Transformers", "PyTorch", "Transformers", "safetensors"],
473
473
  use_instructions=False,
474
474
  # Wikipedia, Books, Twitter comments, Pikabu, Proza.ru, Film subtitles, News websites, and Social corpus
475
475
  public_training_code=None,
@@ -500,7 +500,7 @@ rubert_base_cased = ModelMeta(
500
500
  max_tokens=512,
501
501
  reference="https://huggingface.co/DeepPavlov/rubert-base-cased",
502
502
  similarity_fn_name=ScoringFunction.COSINE,
503
- framework=["Sentence Transformers", "PyTorch"],
503
+ framework=["Sentence Transformers", "PyTorch", "Transformers"],
504
504
  use_instructions=False,
505
505
  public_training_code=None,
506
506
  public_training_data=None,
@@ -536,7 +536,7 @@ distilrubert_small_cased_conversational = ModelMeta(
536
536
  max_tokens=512,
537
537
  reference="https://huggingface.co/DeepPavlov/distilrubert-small-cased-conversational",
538
538
  similarity_fn_name=ScoringFunction.COSINE,
539
- framework=["Sentence Transformers", "PyTorch"],
539
+ framework=["Sentence Transformers", "PyTorch", "Transformers"],
540
540
  use_instructions=False,
541
541
  public_training_code=None,
542
542
  public_training_data=None,
@@ -571,7 +571,7 @@ rubert_base_cased_sentence = ModelMeta(
571
571
  max_tokens=512,
572
572
  reference="https://huggingface.co/DeepPavlov/rubert-base-cased-sentence",
573
573
  similarity_fn_name=ScoringFunction.COSINE,
574
- framework=["Sentence Transformers", "PyTorch"],
574
+ framework=["Sentence Transformers", "PyTorch", "Transformers"],
575
575
  use_instructions=False,
576
576
  public_training_code=None,
577
577
  public_training_data=None,
@@ -596,7 +596,7 @@ labse_en_ru = ModelMeta(
596
596
  max_tokens=512,
597
597
  reference="https://huggingface.co/cointegrated/LaBSE-en-ru",
598
598
  similarity_fn_name=ScoringFunction.COSINE,
599
- framework=["Sentence Transformers", "PyTorch"],
599
+ framework=["Sentence Transformers", "PyTorch", "Transformers", "safetensors"],
600
600
  use_instructions=False,
601
601
  public_training_code="https://colab.research.google.com/drive/1dnPRn0-ugj3vZgSpyCC9sgslM2SuSfHy?usp=sharing",
602
602
  public_training_data=None,
@@ -624,7 +624,7 @@ rubert_tiny_turbo = ModelMeta(
624
624
  max_tokens=2048,
625
625
  reference="https://huggingface.co/sergeyzh/rubert-tiny-turbo",
626
626
  similarity_fn_name=ScoringFunction.COSINE,
627
- framework=["Sentence Transformers", "PyTorch"],
627
+ framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
628
628
  use_instructions=False,
629
629
  public_training_code=None,
630
630
  public_training_data=None,
@@ -647,7 +647,7 @@ rubert_mini_frida = ModelMeta(
647
647
  max_tokens=2048,
648
648
  reference="https://huggingface.co/sergeyzh/rubert-mini-frida",
649
649
  similarity_fn_name=ScoringFunction.COSINE,
650
- framework=["Sentence Transformers", "PyTorch"],
650
+ framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
651
651
  use_instructions=True,
652
652
  public_training_code=None,
653
653
  public_training_data=None,
@@ -675,7 +675,7 @@ labse_ru_turbo = ModelMeta(
675
675
  max_tokens=512,
676
676
  reference="https://huggingface.co/sergeyzh/LaBSE-ru-turbo",
677
677
  similarity_fn_name=ScoringFunction.COSINE,
678
- framework=["Sentence Transformers", "PyTorch"],
678
+ framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
679
679
  use_instructions=False,
680
680
  training_datasets=turbo_models_datasets,
681
681
  public_training_code=None,
@@ -745,7 +745,7 @@ rosberta_ru_en = ModelMeta(
745
745
  },
746
746
  public_training_data=None,
747
747
  public_training_code=None,
748
- framework=["Sentence Transformers", "PyTorch"],
748
+ framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
749
749
  citation="""@misc{snegirev2024russianfocusedembeddersexplorationrumteb,
750
750
  title={The Russian-focused embedders' exploration: ruMTEB benchmark and Russian embedding model design},
751
751
  author={Artem Snegirev and Maria Tikhonova and Anna Maksimova and Alena Fenogenova and Alexander Abramov},
@@ -895,7 +895,7 @@ frida = ModelMeta(
895
895
  training_datasets=frida_training_datasets,
896
896
  public_training_data=None,
897
897
  public_training_code=None,
898
- framework=["Sentence Transformers", "PyTorch"],
898
+ framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
899
899
  citation=None,
900
900
  )
901
901
 
@@ -924,7 +924,7 @@ giga_embeddings = ModelMeta(
924
924
  max_tokens=4096,
925
925
  reference="https://huggingface.co/ai-sage/Giga-Embeddings-instruct",
926
926
  similarity_fn_name=ScoringFunction.COSINE,
927
- framework=["Sentence Transformers", "PyTorch"],
927
+ framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
928
928
  use_instructions=True,
929
929
  public_training_code=None,
930
930
  public_training_data=None,
@@ -956,7 +956,7 @@ berta = ModelMeta(
956
956
  max_tokens=512,
957
957
  reference="https://huggingface.co/sergeyzh/BERTA",
958
958
  similarity_fn_name=ScoringFunction.COSINE,
959
- framework=["Sentence Transformers", "PyTorch"],
959
+ framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
960
960
  use_instructions=True,
961
961
  training_datasets=berta_training_datasets,
962
962
  public_training_code=None,
@@ -1034,7 +1034,7 @@ user2_small = ModelMeta(
1034
1034
  training_datasets=user2_training_data,
1035
1035
  public_training_data=None,
1036
1036
  public_training_code="https://github.com/BlessedTatonka/some_code/tree/2899f27d51efdf4217fc6453799ff197e9792f1e",
1037
- framework=["Sentence Transformers", "PyTorch"],
1037
+ framework=["Sentence Transformers", "PyTorch", "safetensors"],
1038
1038
  citation="""@misc{deepvk2025user,
1039
1039
  title={USER2},
1040
1040
  author={Malashenko, Boris and Spirin, Egor and Sokolov Andrey},
@@ -1067,7 +1067,7 @@ user2_base = ModelMeta(
1067
1067
  training_datasets=user2_training_data,
1068
1068
  public_training_data=None,
1069
1069
  public_training_code="https://github.com/BlessedTatonka/some_code/tree/2899f27d51efdf4217fc6453799ff197e9792f1e",
1070
- framework=["Sentence Transformers", "PyTorch"],
1070
+ framework=["Sentence Transformers", "PyTorch", "safetensors"],
1071
1071
  citation="""@misc{deepvk2025user,
1072
1072
  title={USER2},
1073
1073
  author={Malashenko, Boris and Spirin, Egor and Sokolov Andrey},
@@ -44,7 +44,7 @@ cl_nagoya_ruri_v3_30m = ModelMeta(
44
44
  max_tokens=8192,
45
45
  reference="https://huggingface.co/cl-nagoya/ruri-v3-30m",
46
46
  similarity_fn_name="cosine",
47
- framework=["PyTorch", "Sentence Transformers"],
47
+ framework=["PyTorch", "Sentence Transformers", "safetensors"],
48
48
  use_instructions=True,
49
49
  superseded_by=None,
50
50
  training_datasets={
@@ -75,7 +75,7 @@ cl_nagoya_ruri_v3_70m = ModelMeta(
75
75
  max_tokens=8192,
76
76
  reference="https://huggingface.co/cl-nagoya/ruri-v3-70m",
77
77
  similarity_fn_name="cosine",
78
- framework=["PyTorch", "Sentence Transformers"],
78
+ framework=["PyTorch", "Sentence Transformers", "safetensors"],
79
79
  use_instructions=True,
80
80
  superseded_by=None,
81
81
  training_datasets={"MrTidyRetrieval", "MIRACLRetrieval"},
@@ -104,7 +104,7 @@ cl_nagoya_ruri_v3_130m = ModelMeta(
104
104
  max_tokens=8192,
105
105
  reference="https://huggingface.co/cl-nagoya/ruri-v3-130m",
106
106
  similarity_fn_name="cosine",
107
- framework=["PyTorch", "Sentence Transformers"],
107
+ framework=["PyTorch", "Sentence Transformers", "safetensors"],
108
108
  use_instructions=True,
109
109
  superseded_by=None,
110
110
  training_datasets={"MrTidyRetrieval", "MIRACLRetrieval"},
@@ -133,7 +133,7 @@ cl_nagoya_ruri_v3_310m = ModelMeta(
133
133
  max_tokens=8192,
134
134
  reference="https://huggingface.co/cl-nagoya/ruri-v3-310m",
135
135
  similarity_fn_name="cosine",
136
- framework=["PyTorch", "Sentence Transformers"],
136
+ framework=["PyTorch", "Sentence Transformers", "safetensors"],
137
137
  use_instructions=True,
138
138
  superseded_by=None,
139
139
  training_datasets={"MrTidyRetrieval", "MIRACLRetrieval"},
@@ -163,7 +163,7 @@ cl_nagoya_ruri_small_v2 = ModelMeta(
163
163
  max_tokens=512,
164
164
  reference="https://huggingface.co/cl-nagoya/ruri-small-v2",
165
165
  similarity_fn_name="cosine",
166
- framework=["PyTorch", "Sentence Transformers"],
166
+ framework=["PyTorch", "Sentence Transformers", "safetensors"],
167
167
  use_instructions=True,
168
168
  adapted_from="line-corporation/line-distilbert-base-japanese",
169
169
  superseded_by=None,
@@ -192,7 +192,7 @@ cl_nagoya_ruri_base_v2 = ModelMeta(
192
192
  max_tokens=512,
193
193
  reference="https://huggingface.co/cl-nagoya/ruri-base-v2",
194
194
  similarity_fn_name="cosine",
195
- framework=["PyTorch", "Sentence Transformers"],
195
+ framework=["PyTorch", "Sentence Transformers", "safetensors"],
196
196
  use_instructions=True,
197
197
  adapted_from="tohoku-nlp/bert-base-japanese-v3",
198
198
  superseded_by=None,
@@ -221,7 +221,7 @@ cl_nagoya_ruri_large_v2 = ModelMeta(
221
221
  max_tokens=512,
222
222
  reference="https://huggingface.co/cl-nagoya/ruri-large-v2",
223
223
  similarity_fn_name="cosine",
224
- framework=["PyTorch", "Sentence Transformers"],
224
+ framework=["PyTorch", "Sentence Transformers", "safetensors"],
225
225
  use_instructions=True,
226
226
  adapted_from="tohoku-nlp/bert-large-japanese-v2",
227
227
  superseded_by=None,
@@ -251,7 +251,7 @@ cl_nagoya_ruri_small_v1 = ModelMeta(
251
251
  max_tokens=512,
252
252
  reference="https://huggingface.co/cl-nagoya/ruri-small",
253
253
  similarity_fn_name="cosine",
254
- framework=["PyTorch", "Sentence Transformers"],
254
+ framework=["PyTorch", "Sentence Transformers", "safetensors"],
255
255
  use_instructions=True,
256
256
  adapted_from="line-corporation/line-distilbert-base-japanese",
257
257
  superseded_by="cl-nagoya/ruri-small-v2",
@@ -280,7 +280,7 @@ cl_nagoya_ruri_base_v1 = ModelMeta(
280
280
  max_tokens=512,
281
281
  reference="https://huggingface.co/cl-nagoya/ruri-base",
282
282
  similarity_fn_name="cosine",
283
- framework=["PyTorch", "Sentence Transformers"],
283
+ framework=["PyTorch", "Sentence Transformers", "safetensors"],
284
284
  use_instructions=True,
285
285
  adapted_from="tohoku-nlp/bert-base-japanese-v3",
286
286
  superseded_by="cl-nagoya/ruri-base-v2",
@@ -310,7 +310,7 @@ cl_nagoya_ruri_large_v1 = ModelMeta(
310
310
  max_tokens=512,
311
311
  reference="https://huggingface.co/cl-nagoya/ruri-large",
312
312
  similarity_fn_name="cosine",
313
- framework=["PyTorch", "Sentence Transformers"],
313
+ framework=["PyTorch", "Sentence Transformers", "safetensors"],
314
314
  use_instructions=True,
315
315
  adapted_from="tohoku-nlp/bert-large-japanese-v2",
316
316
  superseded_by="cl-nagoya/ruri-large-v2",
@@ -58,7 +58,7 @@ SFR_Embedding_2_R = ModelMeta(
58
58
  max_tokens=32768,
59
59
  reference="https://huggingface.co/Salesforce/SFR-Embedding-2_R",
60
60
  similarity_fn_name=ScoringFunction.COSINE,
61
- framework=["Sentence Transformers", "PyTorch"],
61
+ framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
62
62
  use_instructions=True,
63
63
  adapted_from="intfloat/e5-mistral-7b-instruct",
64
64
  public_training_code=None,
@@ -96,7 +96,7 @@ SFR_Embedding_Code_2B_R = ModelMeta(
96
96
  max_tokens=8192,
97
97
  reference="https://huggingface.co/Salesforce/SFR-Embedding-Code-2B_R",
98
98
  similarity_fn_name=ScoringFunction.COSINE,
99
- framework=["Sentence Transformers", "PyTorch"],
99
+ framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
100
100
  use_instructions=True,
101
101
  adapted_from="google/gemma-2-2b-it",
102
102
  public_training_code=None,
@@ -134,7 +134,7 @@ SFR_Embedding_Mistral = ModelMeta(
134
134
  max_tokens=32768,
135
135
  reference="https://huggingface.co/Salesforce/SFR-Embedding-Mistral",
136
136
  similarity_fn_name=ScoringFunction.COSINE,
137
- framework=["Sentence Transformers", "PyTorch"],
137
+ framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
138
138
  use_instructions=True,
139
139
  public_training_code=None,
140
140
  public_training_data=None,
@@ -57,7 +57,7 @@ samilpwc_expr = ModelMeta(
57
57
  max_tokens=514,
58
58
  reference="https://huggingface.co/SamilPwC-AXNode-GenAI/PwC-Embedding_expr",
59
59
  similarity_fn_name="cosine",
60
- framework=["Sentence Transformers", "PyTorch"],
60
+ framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
61
61
  use_instructions=True,
62
62
  public_training_code=None,
63
63
  public_training_data=None,
@@ -130,7 +130,7 @@ sbintuitions_sarashina_embedding_v2_1b = ModelMeta(
130
130
  max_tokens=8192,
131
131
  reference="https://huggingface.co/sbintuitions/sarashina-embedding-v2-1b",
132
132
  similarity_fn_name="cosine",
133
- framework=["Sentence Transformers", "PyTorch"],
133
+ framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
134
134
  use_instructions=True,
135
135
  adapted_from="sbintuitions/sarashina2.2-1b",
136
136
  superseded_by=None,
@@ -156,7 +156,7 @@ sbintuitions_sarashina_embedding_v1_1b = ModelMeta(
156
156
  max_tokens=8192,
157
157
  reference="https://huggingface.co/sbintuitions/sarashina-embedding-v1-1b",
158
158
  similarity_fn_name="cosine",
159
- framework=["Sentence Transformers", "PyTorch"],
159
+ framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
160
160
  use_instructions=False,
161
161
  adapted_from="sbintuitions/sarashina2.1-1b",
162
162
  superseded_by="sbintuitions/sarashina-embedding-v2-1b",
@@ -33,7 +33,7 @@ searchmap_preview = ModelMeta(
33
33
  max_tokens=8192,
34
34
  reference="https://huggingface.co/VPLabs/SearchMap_Preview",
35
35
  similarity_fn_name="cosine",
36
- framework=["Sentence Transformers", "PyTorch"],
36
+ framework=["Sentence Transformers", "PyTorch", "Transformers", "safetensors"],
37
37
  public_training_code=None,
38
38
  public_training_data=None,
39
39
  training_datasets=None,