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.
- mteb/abstasks/classification.py +2 -3
- mteb/abstasks/multilabel_classification.py +3 -3
- mteb/abstasks/regression.py +1 -1
- mteb/abstasks/retrieval.py +1 -1
- mteb/abstasks/task_metadata.py +9 -14
- mteb/models/model_implementations/align_models.py +1 -1
- mteb/models/model_implementations/andersborges.py +2 -2
- mteb/models/model_implementations/ara_models.py +1 -1
- mteb/models/model_implementations/arctic_models.py +8 -8
- mteb/models/model_implementations/b1ade_models.py +1 -1
- mteb/models/model_implementations/bge_models.py +45 -21
- mteb/models/model_implementations/bica_model.py +3 -3
- mteb/models/model_implementations/blip2_models.py +2 -2
- mteb/models/model_implementations/blip_models.py +8 -8
- mteb/models/model_implementations/bmretriever_models.py +4 -4
- mteb/models/model_implementations/cadet_models.py +1 -1
- mteb/models/model_implementations/cde_models.py +2 -2
- mteb/models/model_implementations/clip_models.py +3 -3
- mteb/models/model_implementations/clips_models.py +3 -3
- mteb/models/model_implementations/codefuse_models.py +5 -5
- mteb/models/model_implementations/codesage_models.py +3 -3
- mteb/models/model_implementations/cohere_models.py +4 -4
- mteb/models/model_implementations/colpali_models.py +3 -3
- mteb/models/model_implementations/colqwen_models.py +8 -8
- mteb/models/model_implementations/colsmol_models.py +2 -2
- mteb/models/model_implementations/conan_models.py +1 -1
- mteb/models/model_implementations/dino_models.py +19 -19
- mteb/models/model_implementations/e5_instruct.py +23 -4
- mteb/models/model_implementations/e5_models.py +9 -9
- mteb/models/model_implementations/e5_v.py +1 -1
- mteb/models/model_implementations/eagerworks_models.py +1 -1
- mteb/models/model_implementations/emillykkejensen_models.py +3 -3
- mteb/models/model_implementations/en_code_retriever.py +1 -1
- mteb/models/model_implementations/euler_models.py +2 -2
- mteb/models/model_implementations/fa_models.py +9 -9
- mteb/models/model_implementations/facebookai.py +14 -2
- mteb/models/model_implementations/geogpt_models.py +1 -1
- mteb/models/model_implementations/gme_v_models.py +2 -2
- mteb/models/model_implementations/google_models.py +1 -1
- mteb/models/model_implementations/granite_vision_embedding_models.py +1 -1
- mteb/models/model_implementations/gritlm_models.py +2 -2
- mteb/models/model_implementations/gte_models.py +25 -13
- mteb/models/model_implementations/hinvec_models.py +1 -1
- mteb/models/model_implementations/ibm_granite_models.py +30 -6
- mteb/models/model_implementations/inf_models.py +2 -2
- mteb/models/model_implementations/jasper_models.py +2 -2
- mteb/models/model_implementations/jina_clip.py +1 -1
- mteb/models/model_implementations/jina_models.py +11 -5
- mteb/models/model_implementations/kblab.py +12 -6
- mteb/models/model_implementations/kennethenevoldsen_models.py +2 -2
- mteb/models/model_implementations/kfst.py +1 -1
- mteb/models/model_implementations/kowshik24_models.py +1 -1
- mteb/models/model_implementations/lgai_embedding_models.py +1 -1
- mteb/models/model_implementations/linq_models.py +1 -1
- mteb/models/model_implementations/listconranker.py +1 -1
- mteb/models/model_implementations/llm2clip_models.py +3 -3
- mteb/models/model_implementations/llm2vec_models.py +8 -8
- mteb/models/model_implementations/mdbr_models.py +14 -2
- mteb/models/model_implementations/misc_models.py +68 -68
- mteb/models/model_implementations/mme5_models.py +1 -1
- mteb/models/model_implementations/moco_models.py +2 -2
- mteb/models/model_implementations/mod_models.py +1 -1
- mteb/models/model_implementations/model2vec_models.py +13 -13
- mteb/models/model_implementations/moka_models.py +1 -1
- mteb/models/model_implementations/mxbai_models.py +16 -3
- mteb/models/model_implementations/nbailab.py +3 -3
- mteb/models/model_implementations/no_instruct_sentence_models.py +1 -1
- mteb/models/model_implementations/nomic_models.py +18 -6
- mteb/models/model_implementations/nomic_models_vision.py +1 -1
- mteb/models/model_implementations/nvidia_llama_nemoretriever_colemb.py +2 -2
- mteb/models/model_implementations/nvidia_models.py +3 -3
- mteb/models/model_implementations/octen_models.py +2 -2
- mteb/models/model_implementations/openclip_models.py +6 -6
- mteb/models/model_implementations/opensearch_neural_sparse_models.py +5 -5
- mteb/models/model_implementations/ops_moa_models.py +1 -1
- mteb/models/model_implementations/ordalietech_solon_embeddings_mini_beta_1_1.py +1 -1
- mteb/models/model_implementations/pawan_models.py +1 -1
- mteb/models/model_implementations/piccolo_models.py +1 -1
- mteb/models/model_implementations/promptriever_models.py +4 -4
- mteb/models/model_implementations/pylate_models.py +5 -5
- mteb/models/model_implementations/qodo_models.py +2 -2
- mteb/models/model_implementations/qtack_models.py +1 -1
- mteb/models/model_implementations/qwen3_models.py +3 -3
- mteb/models/model_implementations/qzhou_models.py +2 -2
- mteb/models/model_implementations/rasgaard_models.py +1 -1
- mteb/models/model_implementations/reasonir_model.py +1 -1
- mteb/models/model_implementations/repllama_models.py +1 -1
- mteb/models/model_implementations/rerankers_custom.py +9 -3
- mteb/models/model_implementations/rerankers_monot5_based.py +14 -14
- mteb/models/model_implementations/richinfoai_models.py +1 -1
- mteb/models/model_implementations/ru_sentence_models.py +20 -20
- mteb/models/model_implementations/ruri_models.py +10 -10
- mteb/models/model_implementations/salesforce_models.py +3 -3
- mteb/models/model_implementations/samilpwc_models.py +1 -1
- mteb/models/model_implementations/sarashina_embedding_models.py +2 -2
- mteb/models/model_implementations/searchmap_models.py +1 -1
- mteb/models/model_implementations/sentence_transformers_models.py +58 -22
- mteb/models/model_implementations/shuu_model.py +1 -1
- mteb/models/model_implementations/siglip_models.py +10 -10
- mteb/models/model_implementations/slm_models.py +416 -0
- mteb/models/model_implementations/spartan8806_atles_champion.py +1 -1
- mteb/models/model_implementations/stella_models.py +17 -4
- mteb/models/model_implementations/tarka_models.py +2 -2
- mteb/models/model_implementations/text2vec_models.py +9 -3
- mteb/models/model_implementations/ua_sentence_models.py +1 -1
- mteb/models/model_implementations/uae_models.py +7 -1
- mteb/models/model_implementations/vdr_models.py +1 -1
- mteb/models/model_implementations/vi_vn_models.py +6 -6
- mteb/models/model_implementations/vlm2vec_models.py +2 -2
- mteb/models/model_implementations/youtu_models.py +1 -1
- mteb/models/model_implementations/yuan_models.py +1 -1
- mteb/models/model_implementations/yuan_models_en.py +1 -1
- mteb/models/model_meta.py +46 -17
- mteb/results/benchmark_results.py +2 -2
- mteb/tasks/classification/kur/kurdish_sentiment_classification.py +2 -2
- mteb/tasks/clustering/eng/hume_wiki_cities_clustering.py +1 -1
- mteb/tasks/clustering/eng/wiki_cities_clustering.py +1 -1
- mteb/tasks/clustering/zho/cmteb_clustering.py +2 -2
- mteb/tasks/reranking/multilingual/wikipedia_reranking_multilingual.py +1 -1
- mteb/tasks/retrieval/eng/cub200_i2i_retrieval.py +1 -1
- {mteb-2.6.4.dist-info → mteb-2.6.5.dist-info}/METADATA +3 -1
- {mteb-2.6.4.dist-info → mteb-2.6.5.dist-info}/RECORD +126 -125
- {mteb-2.6.4.dist-info → mteb-2.6.5.dist-info}/WHEEL +0 -0
- {mteb-2.6.4.dist-info → mteb-2.6.5.dist-info}/entry_points.txt +0 -0
- {mteb-2.6.4.dist-info → mteb-2.6.5.dist-info}/licenses/LICENSE +0 -0
- {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=[
|
|
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,
|