mteb 2.3.10__py3-none-any.whl → 2.4.1__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 (53) hide show
  1. mteb/_evaluators/image/imagetext_pairclassification_evaluator.py +7 -2
  2. mteb/abstasks/_statistics_calculation.py +6 -2
  3. mteb/abstasks/classification.py +0 -2
  4. mteb/benchmarks/benchmarks/__init__.py +2 -0
  5. mteb/benchmarks/benchmarks/benchmarks.py +57 -0
  6. mteb/deprecated_evaluator.py +8 -13
  7. mteb/descriptive_stats/Reranking/JQaRARerankingLite.json +35 -0
  8. mteb/descriptive_stats/Reranking/JaCWIRRerankingLite.json +35 -0
  9. mteb/descriptive_stats/Retrieval/JaCWIRRetrievalLite.json +30 -0
  10. mteb/descriptive_stats/Retrieval/JaqketRetrievalLite.json +30 -0
  11. mteb/descriptive_stats/Retrieval/MIRACLJaRetrievalLite.json +30 -0
  12. mteb/descriptive_stats/Retrieval/MrTyDiJaRetrievalLite.json +30 -0
  13. mteb/evaluate.py +2 -33
  14. mteb/leaderboard/figures.py +1 -1
  15. mteb/leaderboard/table.py +1 -11
  16. mteb/models/abs_encoder.py +21 -17
  17. mteb/models/cache_wrappers/cache_backends/_hash_utils.py +2 -2
  18. mteb/models/get_model_meta.py +3 -123
  19. mteb/models/instruct_wrapper.py +2 -1
  20. mteb/models/model_implementations/bica_model.py +34 -0
  21. mteb/models/model_implementations/colpali_models.py +7 -2
  22. mteb/models/model_implementations/colqwen_models.py +1 -1
  23. mteb/models/model_implementations/gme_v_models.py +9 -5
  24. mteb/models/model_implementations/google_models.py +10 -0
  25. mteb/models/model_implementations/granite_vision_embedding_models.py +6 -2
  26. mteb/models/model_implementations/jasper_models.py +2 -2
  27. mteb/models/model_implementations/jina_models.py +1 -1
  28. mteb/models/model_implementations/mod_models.py +204 -0
  29. mteb/models/model_implementations/nomic_models.py +142 -4
  30. mteb/models/model_implementations/nomic_models_vision.py +6 -2
  31. mteb/models/model_implementations/nvidia_llama_nemoretriever_colemb.py +6 -2
  32. mteb/models/model_implementations/pylate_models.py +1 -4
  33. mteb/models/model_implementations/random_baseline.py +6 -2
  34. mteb/models/model_implementations/seed_1_6_embedding_models.py +7 -2
  35. mteb/models/model_implementations/voyage_v.py +6 -2
  36. mteb/models/model_meta.py +396 -19
  37. mteb/models/sentence_transformer_wrapper.py +2 -7
  38. mteb/tasks/reranking/jpn/__init__.py +9 -1
  39. mteb/tasks/reranking/jpn/j_qa_ra_reranking_lite.py +49 -0
  40. mteb/tasks/reranking/jpn/ja_cwir_reranking_lite.py +47 -0
  41. mteb/tasks/retrieval/code/fresh_stack_retrieval.py +8 -5
  42. mteb/tasks/retrieval/jpn/__init__.py +8 -0
  43. mteb/tasks/retrieval/jpn/ja_cwir_retrieval_lite.py +47 -0
  44. mteb/tasks/retrieval/jpn/jaqket_retrieval_lite.py +50 -0
  45. mteb/tasks/retrieval/jpn/miracl_ja_retrieval_lite.py +52 -0
  46. mteb/tasks/retrieval/jpn/mr_tydi_ja_retrieval_lite.py +48 -0
  47. mteb/types/_encoder_io.py +7 -2
  48. {mteb-2.3.10.dist-info → mteb-2.4.1.dist-info}/METADATA +2 -1
  49. {mteb-2.3.10.dist-info → mteb-2.4.1.dist-info}/RECORD +53 -39
  50. {mteb-2.3.10.dist-info → mteb-2.4.1.dist-info}/WHEEL +0 -0
  51. {mteb-2.3.10.dist-info → mteb-2.4.1.dist-info}/entry_points.txt +0 -0
  52. {mteb-2.3.10.dist-info → mteb-2.4.1.dist-info}/licenses/LICENSE +0 -0
  53. {mteb-2.3.10.dist-info → mteb-2.4.1.dist-info}/top_level.txt +0 -0
@@ -0,0 +1,47 @@
1
+ from mteb.abstasks.retrieval import AbsTaskRetrieval
2
+ from mteb.abstasks.task_metadata import TaskMetadata
3
+
4
+
5
+ class JaCWIRRetrievalLite(AbsTaskRetrieval):
6
+ metadata = TaskMetadata(
7
+ name="JaCWIRRetrievalLite",
8
+ dataset={
9
+ "path": "mteb/JaCWIRRetrievalLite",
10
+ "revision": "79472b360242cf2692e24a6d9999ef50d350d672",
11
+ },
12
+ description=(
13
+ "JaCWIR (Japanese Casual Web IR) is a dataset consisting of questions and webpage meta descriptions "
14
+ "collected from Hatena Bookmark. This is the lightweight version with a reduced corpus "
15
+ "(302,638 documents) constructed using hard negatives from 5 high-performance models."
16
+ ),
17
+ reference="https://huggingface.co/datasets/hotchpotch/JaCWIR",
18
+ type="Retrieval",
19
+ category="t2t",
20
+ modalities=["text"],
21
+ eval_splits=["test"],
22
+ eval_langs=["jpn-Jpan"],
23
+ main_score="ndcg_at_10",
24
+ date=("2020-01-01", "2025-01-01"),
25
+ domains=["Web", "Written"],
26
+ task_subtypes=["Article retrieval"],
27
+ license="not specified",
28
+ annotations_creators="derived",
29
+ dialect=[],
30
+ sample_creation="found",
31
+ adapted_from=["JaCWIRRetrieval"],
32
+ bibtex_citation=r"""
33
+ @misc{jmteb_lite,
34
+ author = {Li, Shengzhe and Ohagi, Masaya and Ri, Ryokan and Fukuchi, Akihiko and Shibata, Tomohide
35
+ and Kawahara, Daisuke},
36
+ howpublished = {\url{https://huggingface.co/datasets/sbintuitions/JMTEB-lite}},
37
+ title = {{J}{M}{T}{E}{B}-lite: {T}he {L}ightweight {V}ersion of {JMTEB}},
38
+ year = {2025},
39
+ }
40
+
41
+ @misc{yuichi-tateno-2024-jacwir,
42
+ author = {Yuichi Tateno},
43
+ title = {JaCWIR: Japanese Casual Web IR - 日本語情報検索評価のための小規模でカジュアルなWebタイトルと概要のデータセット},
44
+ url = {https://huggingface.co/datasets/hotchpotch/JaCWIR},
45
+ }
46
+ """,
47
+ )
@@ -0,0 +1,50 @@
1
+ from mteb.abstasks.retrieval import AbsTaskRetrieval
2
+ from mteb.abstasks.task_metadata import TaskMetadata
3
+
4
+
5
+ class JaqketRetrievalLite(AbsTaskRetrieval):
6
+ metadata = TaskMetadata(
7
+ name="JaqketRetrievalLite",
8
+ dataset={
9
+ "path": "mteb/JaqketRetrievalLite",
10
+ "revision": "860965fbb6526dd8edff12627dacf07c8f5a54f3",
11
+ },
12
+ description=(
13
+ "JAQKET (JApanese Questions on Knowledge of EnTities) is a QA dataset created based on quiz questions. "
14
+ "This is the lightweight version with a reduced corpus (65,802 documents) constructed using "
15
+ "hard negatives from 5 high-performance models."
16
+ ),
17
+ reference="https://github.com/kumapo/JAQKET-dataset",
18
+ type="Retrieval",
19
+ category="t2t",
20
+ modalities=["text"],
21
+ eval_splits=["test"],
22
+ eval_langs=["jpn-Jpan"],
23
+ main_score="ndcg_at_10",
24
+ date=("2023-10-09", "2025-01-01"),
25
+ domains=["Encyclopaedic", "Non-fiction", "Written"],
26
+ task_subtypes=["Question answering"],
27
+ license="cc-by-sa-4.0",
28
+ annotations_creators="human-annotated",
29
+ dialect=[],
30
+ sample_creation="found",
31
+ adapted_from=["JaqketRetrieval"],
32
+ bibtex_citation=r"""
33
+ @misc{jmteb_lite,
34
+ author = {Li, Shengzhe and Ohagi, Masaya and Ri, Ryokan and Fukuchi, Akihiko and Shibata, Tomohide
35
+ and Kawahara, Daisuke},
36
+ howpublished = {\url{https://huggingface.co/datasets/sbintuitions/JMTEB-lite}},
37
+ title = {{J}{M}{T}{E}{B}-lite: {T}he {L}ightweight {V}ersion of {JMTEB}},
38
+ year = {2025},
39
+ }
40
+
41
+ @inproceedings{Kurihara_nlp2020,
42
+ author = {鈴木正敏 and 鈴木潤 and 松田耕史 and ⻄田京介 and 井之上直也},
43
+ booktitle = {言語処理学会第26回年次大会},
44
+ note = {in Japanese},
45
+ title = {JAQKET: クイズを題材にした日本語 QA データセットの構築},
46
+ url = {https://www.anlp.jp/proceedings/annual_meeting/2020/pdf_dir/P2-24.pdf},
47
+ year = {2020},
48
+ }
49
+ """,
50
+ )
@@ -0,0 +1,52 @@
1
+ from mteb.abstasks.retrieval import AbsTaskRetrieval
2
+ from mteb.abstasks.task_metadata import TaskMetadata
3
+
4
+
5
+ class MIRACLJaRetrievalLite(AbsTaskRetrieval):
6
+ metadata = TaskMetadata(
7
+ name="MIRACLJaRetrievalLite",
8
+ dataset={
9
+ "path": "mteb/MIRACLJaRetrievalLite",
10
+ "revision": "575c225da29d1f5fec01082afa56f35df0f44295",
11
+ },
12
+ description=(
13
+ "MIRACL (Multilingual Information Retrieval Across a Continuum of Languages) is a multilingual "
14
+ "retrieval dataset. This is the lightweight Japanese version with a reduced corpus (105,064 documents) "
15
+ "constructed using hard negatives from 5 high-performance models."
16
+ ),
17
+ reference="https://project-miracl.github.io/",
18
+ type="Retrieval",
19
+ category="t2t",
20
+ modalities=["text"],
21
+ eval_splits=["test"],
22
+ eval_langs=["jpn-Jpan"],
23
+ main_score="ndcg_at_10",
24
+ date=("2022-06-01", "2025-01-01"),
25
+ domains=["Encyclopaedic", "Written"],
26
+ task_subtypes=[],
27
+ license="apache-2.0",
28
+ annotations_creators="expert-annotated",
29
+ dialect=[],
30
+ sample_creation="created",
31
+ adapted_from=["MIRACLRetrieval"],
32
+ bibtex_citation=r"""
33
+ @article{10.1162/tacl_a_00595,
34
+ author = {Zhang, Xinyu and Thakur, Nandan and Ogundepo, Odunayo and Kamalloo, Ehsan and Alfonso-Hermelo, David
35
+ and Li, Xiaoguang and Liu, Qun and Rezagholizadeh, Mehdi and Lin, Jimmy},
36
+ doi = {10.1162/tacl_a_00595},
37
+ journal = {Transactions of the Association for Computational Linguistics},
38
+ pages = {1114-1131},
39
+ title = {{MIRACL: A Multilingual Retrieval Dataset Covering 18 Diverse Languages}},
40
+ volume = {11},
41
+ year = {2023},
42
+ }
43
+
44
+ @misc{jmteb_lite,
45
+ author = {Li, Shengzhe and Ohagi, Masaya and Ri, Ryokan and Fukuchi, Akihiko and Shibata, Tomohide
46
+ and Kawahara, Daisuke},
47
+ howpublished = {\url{https://huggingface.co/datasets/sbintuitions/JMTEB-lite}},
48
+ title = {{J}{M}{T}{E}{B}-lite: {T}he {L}ightweight {V}ersion of {JMTEB}},
49
+ year = {2025},
50
+ }
51
+ """,
52
+ )
@@ -0,0 +1,48 @@
1
+ from mteb.abstasks.retrieval import AbsTaskRetrieval
2
+ from mteb.abstasks.task_metadata import TaskMetadata
3
+
4
+
5
+ class MrTyDiJaRetrievalLite(AbsTaskRetrieval):
6
+ metadata = TaskMetadata(
7
+ name="MrTyDiJaRetrievalLite",
8
+ dataset={
9
+ "path": "mteb/MrTyDiJaRetrievalLite",
10
+ "revision": "b87e6ff25f4e32d1c97498a539ea8aad5fde3cb1",
11
+ },
12
+ description=(
13
+ "Mr.TyDi is a multilingual benchmark dataset built on TyDi for document retrieval tasks. "
14
+ "This is the lightweight Japanese version with a reduced corpus (93,382 documents) constructed using "
15
+ "hard negatives from 5 high-performance models."
16
+ ),
17
+ reference="https://huggingface.co/datasets/castorini/mr-tydi",
18
+ type="Retrieval",
19
+ category="t2t",
20
+ modalities=["text"],
21
+ eval_splits=["test"],
22
+ eval_langs=["jpn-Jpan"],
23
+ main_score="ndcg_at_10",
24
+ date=("2021-01-01", "2025-01-01"),
25
+ domains=["Encyclopaedic", "Non-fiction", "Written"],
26
+ task_subtypes=["Question answering"],
27
+ license="apache-2.0",
28
+ annotations_creators="human-annotated",
29
+ dialect=[],
30
+ sample_creation="found",
31
+ adapted_from=["MrTidyRetrieval"],
32
+ bibtex_citation=r"""
33
+ @misc{jmteb_lite,
34
+ author = {Li, Shengzhe and Ohagi, Masaya and Ri, Ryokan and Fukuchi, Akihiko and Shibata, Tomohide
35
+ and Kawahara, Daisuke},
36
+ howpublished = {\url{https://huggingface.co/datasets/sbintuitions/JMTEB-lite}},
37
+ title = {{J}{M}{T}{E}{B}-lite: {T}he {L}ightweight {V}ersion of {JMTEB}},
38
+ year = {2025},
39
+ }
40
+
41
+ @article{mrtydi,
42
+ author = {Xinyu Zhang and Xueguang Ma and Peng Shi and Jimmy Lin},
43
+ journal = {arXiv:2108.08787},
44
+ title = {{Mr. TyDi}: A Multi-lingual Benchmark for Dense Retrieval},
45
+ year = {2021},
46
+ }
47
+ """,
48
+ )
mteb/types/_encoder_io.py CHANGED
@@ -1,13 +1,18 @@
1
+ from __future__ import annotations
2
+
1
3
  from collections.abc import Mapping
2
4
  from enum import Enum
3
- from typing import TypedDict
5
+ from typing import TYPE_CHECKING, TypedDict
4
6
 
5
7
  import numpy as np
6
8
  import torch
7
9
  from datasets import Dataset
8
- from PIL import Image
9
10
  from typing_extensions import NotRequired
10
11
 
12
+ if TYPE_CHECKING:
13
+ from PIL import Image
14
+
15
+
11
16
  # --- Output types ---
12
17
  Array = np.ndarray | torch.Tensor
13
18
  """General array type, can be a numpy array or a torch tensor."""
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: mteb
3
- Version: 2.3.10
3
+ Version: 2.4.1
4
4
  Summary: Massive Text Embedding Benchmark
5
5
  Author-email: MTEB Contributors <niklas@huggingface.co>, Kenneth Enevoldsen <kenneth.enevoldsen@cas.au.dk>, Nouamane Tazi <nouamane@huggingface.co>, Nils Reimers <info@nils-reimers.de>
6
6
  Maintainer-email: Kenneth Enevoldsen <kenneth.enevoldsen@cas.au.dk>, Roman Solomatin <risolomatin@gmail.com>, Isaac Chung <chungisaac1217@gmail.com>
@@ -34,6 +34,7 @@ Requires-Dist: pydantic>=2.0.0
34
34
  Requires-Dist: polars>=0.20.22
35
35
  Provides-Extra: image
36
36
  Requires-Dist: torchvision>0.2.1; extra == "image"
37
+ Requires-Dist: transformers[torch-vision,vision]; extra == "image"
37
38
  Provides-Extra: codecarbon
38
39
  Requires-Dist: codecarbon<3.0.0,>=2.0.0; extra == "codecarbon"
39
40
  Provides-Extra: leaderboard
@@ -6,8 +6,8 @@ mteb/_log_once.py,sha256=-tUKzxGQzf2LZSuQXi97oYFXMta1B6GEYXd7BPqssvY,1095
6
6
  mteb/_requires_package.py,sha256=eHg_TD9BVZRzNCcQQrUP17d8M1DF_vOd_tVx54AmAnM,3017
7
7
  mteb/_set_seed.py,sha256=HPlPRl__Pe6IG-4UgJqTfplcivJ_wA2kaClbXoHQedM,1178
8
8
  mteb/cache.py,sha256=XiFuhjZ2C-o0LgP1YM8g9As_vigJCUNfTrOb9-EiFlM,20177
9
- mteb/deprecated_evaluator.py,sha256=t13Eluvm5ByVIOqgT7fqiVfLb8Ud3A4bbF2djRfs8iA,26901
10
- mteb/evaluate.py,sha256=B60CkqRHzkI-3zIfHyocp-YUeWrzeoOvX_RN5vSlGqE,19363
9
+ mteb/deprecated_evaluator.py,sha256=9cJIahJHNZphoqo6KZfp30LLhIdyiR3SSLcut4FR_Ek,26778
10
+ mteb/evaluate.py,sha256=IcaNu3VQwoeH7F1m8_7qJ6_lffHPujRcjKOBo4A7JBI,18631
11
11
  mteb/filter_tasks.py,sha256=5XE1OYmgDDoJYnXwFf4ma_PIT_Lekzs420sQF_kpCiY,7240
12
12
  mteb/get_tasks.py,sha256=6Gc18a2bZoLQV1Ms_qdr2KieAqIXg8TDg4l7ZN8rW2I,14218
13
13
  mteb/load_results.py,sha256=Xw2ZX7BToU92WwUTQUQKPAgPhX7ucyRRdoCrxAoPHdI,6414
@@ -24,17 +24,17 @@ mteb/_evaluators/retrieval_metrics.py,sha256=we0damQCJrdaRUD6JlU2MM7Ls9xERP_OBS5
24
24
  mteb/_evaluators/sklearn_evaluator.py,sha256=f9SgBbvgCrkltdTebQTixT7KmIagGkjQ_cNnKuHTb3w,3772
25
25
  mteb/_evaluators/zeroshot_classification_evaluator.py,sha256=dQq6g9my-0xn_0fLJXSnhN9Qu6PuJtWCKGIDrlkeyJk,2282
26
26
  mteb/_evaluators/image/__init__.py,sha256=CsQd7OMkeV2Phun7paPWjayZ5qRnvj8H0TYBFeqMxag,148
27
- mteb/_evaluators/image/imagetext_pairclassification_evaluator.py,sha256=RSJxEIVvOl_Za07fk2jfXE-7QOwKsLOhIyGhZtLVABs,4808
27
+ mteb/_evaluators/image/imagetext_pairclassification_evaluator.py,sha256=lVizL_11s0yFAZzuGqv-wtkBbMaK7cArD1eUkxwG4uU,4883
28
28
  mteb/_evaluators/text/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
29
29
  mteb/_evaluators/text/bitext_mining_evaluator.py,sha256=XS7AVml5-BpQWtG1XFHf6fx8VMVPRwibg-9si4b-A_U,6308
30
30
  mteb/_evaluators/text/summarization_evaluator.py,sha256=l0AwjVO594mtzPV9Kcqf_xtHHpkx6uhDJ61KnolcVAo,10461
31
31
  mteb/abstasks/__init__.py,sha256=1iAwpYTWX7U-goak2KMmacPFCzxPchLQAmZ_uI0t-p0,1130
32
- mteb/abstasks/_statistics_calculation.py,sha256=gf_BhkXbCdwT1w4xza3op6FmjFsZIsNjvyUMCgRyTrg,5578
32
+ mteb/abstasks/_statistics_calculation.py,sha256=UP2H2Cy8yqwtqeimTWfe4unmZ4iyyr5qiBNZzzFjy9o,5669
33
33
  mteb/abstasks/_stratification.py,sha256=zfwkIVmD7Aq7mR2Yt8jTeW1j5ZVV7CIweW842VzcfXc,14364
34
34
  mteb/abstasks/abstask.py,sha256=nZwiY_5d0VVtUrlCATngpFLG3JAovO5AvmD0nkkWsLE,25118
35
35
  mteb/abstasks/aggregate_task_metadata.py,sha256=vzt1z2wDl0sXD7ErZFwKojYwmFUBPAnGlXLuqLA_-6Q,5992
36
36
  mteb/abstasks/aggregated_task.py,sha256=puY6-EAqbL5ehKvFHTMriIdy3rAuqqYHF3ezog1eYxw,6671
37
- mteb/abstasks/classification.py,sha256=Es9pmRdjv6xbc-KnGqVdO6dR1cc7yAHhekCZES7n5o8,13441
37
+ mteb/abstasks/classification.py,sha256=k_wrM1rq2XcVEK97RpU_uEcqhiWWbV7sm3B0dtvP5yY,13376
38
38
  mteb/abstasks/clustering.py,sha256=4KcaU8_sNLmLvMhwDpNmcY2nD3BNyx_LcM-ddSv-wtY,14410
39
39
  mteb/abstasks/clustering_legacy.py,sha256=HZY8zgBgqqs5urF_to9wzqm3MnjFivs59hU6P3NrzcI,8684
40
40
  mteb/abstasks/dataset_card_template.md,sha256=aD6l8qc3_jxwoIGJNYLzse-jpRa8hu92AxpnUtNgges,5122
@@ -59,8 +59,8 @@ mteb/benchmarks/__init__.py,sha256=MQEVeli-zLaJ7Xg0z7RhXQwsdmm7Ht_W2Ln0rZo1Szc,2
59
59
  mteb/benchmarks/_create_table.py,sha256=b2RqGqi0ZonKbHecEcZiF4pkfE96smFRIzxOI82ETA8,22304
60
60
  mteb/benchmarks/benchmark.py,sha256=UEllUtZQ0L10SNnxRyKbiv4wLCMcNF2nUPhBDKY3nz8,5097
61
61
  mteb/benchmarks/get_benchmark.py,sha256=-n_O-gitRKZi48gJKNgGuI36hsP7yLVSiwulnMHN7Gw,3935
62
- mteb/benchmarks/benchmarks/__init__.py,sha256=Ig5dSFunzI-F-OamruuKJVSstbG3xQNkXCxRY3Bj_Ck,2180
63
- mteb/benchmarks/benchmarks/benchmarks.py,sha256=mZQ56KBQwnBj2qLSQFOv39Av0HBNpH9HXYsDoFmqvu4,95640
62
+ mteb/benchmarks/benchmarks/__init__.py,sha256=73NYNv98q-tRCqf2YHabvElz_a8g_mF75HTup0J-E5E,2220
63
+ mteb/benchmarks/benchmarks/benchmarks.py,sha256=KuXEjB7-3S4b7sChJGmzt2z5iviujRxfqZx5kKNeQAc,97968
64
64
  mteb/benchmarks/benchmarks/rteb_benchmarks.py,sha256=QnCSrTTaBfcRlAQp2Nu81tgv1idMXqiM16Fp2zKJ5Ys,10607
65
65
  mteb/cli/__init__.py,sha256=v-csUr3eUZElIvrGB6QGtaIdndDfNWEe9oZchsGsJpg,64
66
66
  mteb/cli/_display_tasks.py,sha256=7A06dT9sSoTz6shyMvskPxuc5eHY_H7PGPlROzMP0yw,2196
@@ -959,7 +959,9 @@ mteb/descriptive_stats/Reranking/HUMENews21InstructionReranking.json,sha256=8R-4
959
959
  mteb/descriptive_stats/Reranking/HUMERobust04InstructionReranking.json,sha256=Wk9-8xNePKEImoy3UkRasid58gai-e6gIlkzO_VIjIc,1156
960
960
  mteb/descriptive_stats/Reranking/HUMEWikipediaRerankingMultilingual.json,sha256=7HSs-XvtdORejbHXbBu6GjPSRPYnemI-r3aWIdauwUo,5448
961
961
  mteb/descriptive_stats/Reranking/JQaRAReranking.json,sha256=jH5RuOb36a-gH_QNh0DZQpofpyoYGkjKQm9iFn7-VUM,1201
962
+ mteb/descriptive_stats/Reranking/JQaRARerankingLite.json,sha256=pQFLnAx3zUt1AzlpkQhvI-Hix9rr_3dQ0WEmdUPKL6o,1205
962
963
  mteb/descriptive_stats/Reranking/JaCWIRReranking.json,sha256=N4djULyJD_lgJa8x-qoACiaL33hUjdLK02hqXv7Bv5M,1169
964
+ mteb/descriptive_stats/Reranking/JaCWIRRerankingLite.json,sha256=CC6F5QTDt5dwroOBvm6h2FObxeCHifraGAZTzwLnUcc,1175
963
965
  mteb/descriptive_stats/Reranking/LocBenchRR.json,sha256=k3Jck8QfSBxrsDenSgT06T2CbTSs8SGH2Y_RBrDWiTs,1227
964
966
  mteb/descriptive_stats/Reranking/MIRACLReranking.json,sha256=boUEIFlFgCUG40M2-mXuXkJluK2POQYuoJYMXPdatVQ,27457
965
967
  mteb/descriptive_stats/Reranking/MMarcoReranking.json,sha256=XF75mWbGFkCCOxgvgy04PWgd7AiHBvCrBGPumK_gKIk,1173
@@ -1180,11 +1182,13 @@ mteb/descriptive_stats/Retrieval/HumanEvalRetrieval.json,sha256=aiW3AaImNrsEfUUp
1180
1182
  mteb/descriptive_stats/Retrieval/HunSum2AbstractiveRetrieval.json,sha256=o3FOm7CJmMUGsdfOc8fC2yln3C69WOnG78K13tq90Q0,992
1181
1183
  mteb/descriptive_stats/Retrieval/IndicQARetrieval.json,sha256=Ao6BLg1DeZG0QLGerXX8YlqtoqMqw--G2QvaP2-9wtA,14374
1182
1184
  mteb/descriptive_stats/Retrieval/JaCWIRRetrieval.json,sha256=sJH2BuaFdoxHH0MSqxdE1DCYSyGslvAbrWaanMSqOUA,985
1185
+ mteb/descriptive_stats/Retrieval/JaCWIRRetrievalLite.json,sha256=67G5OL3dGxPgk_oAClj4IYFgo28Zf_GZ4OnMdRy044c,986
1183
1186
  mteb/descriptive_stats/Retrieval/JaGovFaqsRetrieval.json,sha256=CfZmdZfVDZjMqnAcCmgIFKoNHhIENxh0KVPVQe_lDi0,987
1184
1187
  mteb/descriptive_stats/Retrieval/JaQuADRetrieval.json,sha256=-IxLNwbqC0ZSICvLnICXcANdefo-YrE8GSjU5Ir_vsY,986
1185
1188
  mteb/descriptive_stats/Retrieval/JapaneseCode1Retrieval.json,sha256=DkRoV776czj5-d2-ehjZDHDzQhDwA0WVnjuVjRG-h4w,998
1186
1189
  mteb/descriptive_stats/Retrieval/JapaneseLegal1Retrieval.json,sha256=LMZQX5p24p3mGkwqIYbqzGU76_nSGCtRP9aMXjAIc9s,1012
1187
1190
  mteb/descriptive_stats/Retrieval/JaqketRetrieval.json,sha256=LJ0tsK1pov8gtcmfHl7-X8jqi8fIr_tjIMUMEK9YlJ0,993
1191
+ mteb/descriptive_stats/Retrieval/JaqketRetrievalLite.json,sha256=78u8XUaxtWViVgE6TWQRhUljNKx_XJX14S9FQuWzCzM,991
1188
1192
  mteb/descriptive_stats/Retrieval/Ko-StrategyQA.json,sha256=DRJ8rW7y58wIlm8dRHlEiYnrR03Fz-Q9P_Y7y3BOEaw,1001
1189
1193
  mteb/descriptive_stats/Retrieval/LEMBNarrativeQARetrieval.json,sha256=bGyt0faJEvh2TILMC_2qmrCRG37utjOayw3ZpjDNX9Q,1001
1190
1194
  mteb/descriptive_stats/Retrieval/LEMBNeedleRetrieval.json,sha256=f-PHx91WO4YC6q0SqfbMWsH3S1zfhnXYCJZ2kwnQ17M,7685
@@ -1203,6 +1207,7 @@ mteb/descriptive_stats/Retrieval/LegalSummarization.json,sha256=wOTo3a35f0hcHwfw
1203
1207
  mteb/descriptive_stats/Retrieval/LitSearchRetrieval.json,sha256=ws1aeRMer8XyiuYjsBoSgafej46zkeEf3XidAViWbNM,1003
1204
1208
  mteb/descriptive_stats/Retrieval/LoTTE.json,sha256=L4lPCphR0r3_xN4IXQklQdE5NsLo97LsNvRv79rz5ZE,27011
1205
1209
  mteb/descriptive_stats/Retrieval/MBPPRetrieval.json,sha256=jfOr5rVx4304Icglrh-94dXNuGjnxPIqP7e5_v6WRLs,983
1210
+ mteb/descriptive_stats/Retrieval/MIRACLJaRetrievalLite.json,sha256=rcXFC5tqA5KdU8J8mxCKqkpUMY_-qVEgKjCO7yuVZxU,1008
1206
1211
  mteb/descriptive_stats/Retrieval/MIRACLRetrieval.json,sha256=a_tOrkxHdINJY_hXF24COOs5WF39NOgXGGTZgmN_ZpY,23211
1207
1212
  mteb/descriptive_stats/Retrieval/MIRACLRetrievalHardNegatives.json,sha256=bcifWI51GUSkrhbIPCYT7ieV21Wsr1eBSCmZbXkjXCs,23040
1208
1213
  mteb/descriptive_stats/Retrieval/MIRACLRetrievalHardNegatives.v2.json,sha256=bcifWI51GUSkrhbIPCYT7ieV21Wsr1eBSCmZbXkjXCs,23040
@@ -1222,6 +1227,7 @@ mteb/descriptive_stats/Retrieval/MedicalQARetrieval.json,sha256=3mN6T82PDSlpUJB0
1222
1227
  mteb/descriptive_stats/Retrieval/MedicalRetrieval.json,sha256=vMa94jsIhkoTXMsPoHaJuXbBRaPuKto-KYlyHkOKHLM,980
1223
1228
  mteb/descriptive_stats/Retrieval/MintakaRetrieval.json,sha256=1XcaYZBo5VHD6SVmKKzSCUk3FlJQK4uopnBV2epQeWk,10698
1224
1229
  mteb/descriptive_stats/Retrieval/MrTidyRetrieval.json,sha256=X2Jp5nByCv_UNmeeHOpLbE20iGnos9nB_E28D4ZIvhg,14653
1230
+ mteb/descriptive_stats/Retrieval/MrTyDiJaRetrievalLite.json,sha256=Y_6lLFpRcqXCrGYCs19VfwMvpdVFrkqJVBsJvEfokt4,1004
1225
1231
  mteb/descriptive_stats/Retrieval/MultiLongDocRetrieval.json,sha256=MGBeQevI03sxAK3qldfye3yRxQ7O5URV90NFyCNUr_k,33239
1226
1232
  mteb/descriptive_stats/Retrieval/NFCorpus-Fa.json,sha256=rqHqn43MBaA4cni5FbCD5CK_TmQ5z3SiXDmfGx7GIUg,1002
1227
1233
  mteb/descriptive_stats/Retrieval/NFCorpus-NL.json,sha256=x5eYhzWMKToA0ayxP3h10FyegCrbirrCywRQCzMI9SM,1003
@@ -1432,22 +1438,22 @@ mteb/languages/programming_languages.py,sha256=zxAakT3OSUnAuTnQ34VyeFIECnNXMlleZ
1432
1438
  mteb/leaderboard/__init__.py,sha256=991roXmtRwEQysV-37hWEzWpkvPgMCGRqZTHR-hm2io,88
1433
1439
  mteb/leaderboard/app.py,sha256=-sBAkZ9JTr9czhsYEbSm92MfTmB8BOQ17WDkQ1dsP90,34282
1434
1440
  mteb/leaderboard/benchmark_selector.py,sha256=qd-2L20RQ4ACke01UlytkhZok1dkWgfUlXzfET52kGc,7956
1435
- mteb/leaderboard/figures.py,sha256=mPO0go_23QEhAm1RJdLiBxPFCoUiA74_ztyl6yimc7k,7553
1436
- mteb/leaderboard/table.py,sha256=NxXAUkQRWtxjJwfIiO9yvdvw9do3ogzqmAn6az01SSc,10609
1441
+ mteb/leaderboard/figures.py,sha256=cfOK82rRf-7sCjyP7GBxh4ezhOIt0OhD0_86mKtzLrg,7530
1442
+ mteb/leaderboard/table.py,sha256=KqU8aAbZ_tDp1O_qXRGWR32QnB7v_lsF6k5jxLcQVN0,10366
1437
1443
  mteb/leaderboard/text_segments.py,sha256=iMIkS04QQjPbT-SkU0x6fOcS8xRbUYevryu9HydipKM,6570
1438
1444
  mteb/models/__init__.py,sha256=ABTuoqiBjBtBWW3LYY7ItBHdylR6jWoy06HH0g6j6fU,910
1439
- mteb/models/abs_encoder.py,sha256=m0JkRfRPMYadDgBR9eozRloI31ZSWkSzDFINpwbfLZk,16533
1440
- mteb/models/get_model_meta.py,sha256=GeofphZ8wFtwAHYQipgQlZzxNIFAVFGzo_E2sMzjZTc,9350
1441
- mteb/models/instruct_wrapper.py,sha256=Ty4nfEvioycL_uATkhd0PGuyeB5Xc9xrRd6HOGgb-tc,9005
1442
- mteb/models/model_meta.py,sha256=b-Nel9nX5bJk4cgJnqkBzEKyMY7uXvxlCBSxmmH1Ios,14769
1445
+ mteb/models/abs_encoder.py,sha256=XblcGJYJlbTwhX43wvRft_XqnSq2WpzjFcNIwOyRjYo,16443
1446
+ mteb/models/get_model_meta.py,sha256=BMzlqTuzzhIFmfzmtshnRu2KCWxw9mCPyClJfe4oGdQ,5396
1447
+ mteb/models/instruct_wrapper.py,sha256=G4dMcmD5A4M3hmKATf5OYezmZv8-Ie189BrdmipBo7Y,9091
1448
+ mteb/models/model_meta.py,sha256=08jnKQ2-TZ9IFRy_Nx2-tb9eZXMflWN4i3PvNvi5HGw,27899
1443
1449
  mteb/models/models_protocols.py,sha256=D2hYWn_UBGMaKtRwBx3u0B0ni6lHJjSzTxX21XFNwIc,8917
1444
1450
  mteb/models/search_wrappers.py,sha256=zpCvxUVNQWekyC4Fiz7mvlI0VPdSrFq41A0GrCDvBK4,20331
1445
- mteb/models/sentence_transformer_wrapper.py,sha256=n5CMsM6Lpg_CFHH0NkpJusMsaLUTt-L9vRmFINQ961k,12338
1451
+ mteb/models/sentence_transformer_wrapper.py,sha256=xSkFcw6EiCmPJeeMPYm0A0jONRIi0lQc0jBSEhUgXN8,12144
1446
1452
  mteb/models/cache_wrappers/__init__.py,sha256=1w1TnMwulWJSzNkLXjbh5MY3sqgHWc6vUntYn49i9X8,169
1447
1453
  mteb/models/cache_wrappers/cache_backend_protocol.py,sha256=TR7kD7KbN1J4piszIecpegtLZYGy7sRHZt3SDWlImKk,1665
1448
1454
  mteb/models/cache_wrappers/cache_wrapper.py,sha256=KLDeOCe_ndQshbZa5ep2u3jovsl--tfpQzvt9EXyxCA,6589
1449
1455
  mteb/models/cache_wrappers/cache_backends/__init__.py,sha256=hN2Tq7cpTxoOYSCJ1Wnpvb8dEm-kQLfCCahT1N9Bacw,123
1450
- mteb/models/cache_wrappers/cache_backends/_hash_utils.py,sha256=WeQjXlNUpGpb-CbaWpu_EtezML7zoDYfbwIo0Jswvsc,480
1456
+ mteb/models/cache_wrappers/cache_backends/_hash_utils.py,sha256=zAp7BDuYyGETn2kX58uk8_tn1G2B7bgcsItDDxgyn-w,488
1451
1457
  mteb/models/cache_wrappers/cache_backends/faiss_cache.py,sha256=i9IfaCv1-_BvVokXFW1UZ9hMLCuM6rZ0tI-ZesoBkt4,3734
1452
1458
  mteb/models/cache_wrappers/cache_backends/numpy_cache.py,sha256=GyTVC5DLph3EeRnDMO1EEQzBDoOgk2J1hPqpl07lefM,7442
1453
1459
  mteb/models/model_implementations/__init__.py,sha256=BZDdde6ajKv-yroy9mqE2YS3Hw1KBdKoxBPg8aPTZEs,1164
@@ -1459,6 +1465,7 @@ mteb/models/model_implementations/arctic_models.py,sha256=eaMRaN9WdpVq1W6cbtNcJM
1459
1465
  mteb/models/model_implementations/b1ade_models.py,sha256=aEKmXWVX8iJ_OotAYPOMxsOHTDEOJYdSwkR6iJsZ-ms,1609
1460
1466
  mteb/models/model_implementations/bedrock_models.py,sha256=RWN25Es4Nb6eIMiZlFHWNAnftKMVBumM2kozpO7Kh50,8709
1461
1467
  mteb/models/model_implementations/bge_models.py,sha256=LL_JnXsjGPnzzxby05Z0Jm3v6-v76nCB-yI36H9fKwo,22386
1468
+ mteb/models/model_implementations/bica_model.py,sha256=vNO6FiqOhAwUky-_Suq3ZpeJ8GVIsd6-uIU6-Y-wFy8,1227
1462
1469
  mteb/models/model_implementations/blip2_models.py,sha256=hBdilqIIFkILmGoSl6GjT5gpFVxArp3xL3JEcWfJ1KU,7635
1463
1470
  mteb/models/model_implementations/blip_models.py,sha256=n_XRcymbYL2Rx8AFl96OpGQcWvfzrvFQxKvFl4swzA4,11516
1464
1471
  mteb/models/model_implementations/bm25.py,sha256=orjdCPWRdeAskQ3zJEzuNMyEks6WW1qv4mGfw8Ih51Q,4836
@@ -1471,8 +1478,8 @@ mteb/models/model_implementations/codefuse_models.py,sha256=19Y-d_qetVU64quzEvuU
1471
1478
  mteb/models/model_implementations/codesage_models.py,sha256=D4CdISGyv5f2GMYq4_efgm5qNq80SWAX5R2u5mjEiXM,2998
1472
1479
  mteb/models/model_implementations/cohere_models.py,sha256=OWFClVAN4phjBoxfGGDyGDmzMu-t2VrjCGFyAIWmz4w,13832
1473
1480
  mteb/models/model_implementations/cohere_v.py,sha256=K6VEw1NkyM2PuMd18kHE6aqPrcByYSwEmAKjvLods_w,15760
1474
- mteb/models/model_implementations/colpali_models.py,sha256=7PJ0SshVXasyncTfZRFIf_ZWzbqxJhhzNKAoGLhNktw,9004
1475
- mteb/models/model_implementations/colqwen_models.py,sha256=6upaxe19V8j5Ayu03Dgj5jPtC8SJBCITK_RionJRMSE,15545
1481
+ mteb/models/model_implementations/colpali_models.py,sha256=l-0A3J5rt1bhhTKFPQ3Ti0qvWf2qXYkiv3j1si04R8I,9108
1482
+ mteb/models/model_implementations/colqwen_models.py,sha256=wxR3sqyzObuXMlm1QLoFopJK3ZpQTzd3ZB5IrkzPfZk,15553
1476
1483
  mteb/models/model_implementations/colsmol_models.py,sha256=O2M7Ksydh94M_Iax4KytHb-wOL18N0BIYLKSsLF8BFs,2967
1477
1484
  mteb/models/model_implementations/conan_models.py,sha256=G-s7xo9VtNX-f7lWKtYVGHHiMMN0Xp44PlNIp7E0LAo,6502
1478
1485
  mteb/models/model_implementations/dino_models.py,sha256=QFgaFHR5YKrylqJGSljXCBn2W7qHhmF6KdXkvHrQNEI,16380
@@ -1487,18 +1494,18 @@ mteb/models/model_implementations/evaclip_models.py,sha256=cPMGYLDIq4s8zJxb4vPXq
1487
1494
  mteb/models/model_implementations/fa_models.py,sha256=WGal70_ezITWoNdjcMdbOCTSCtoaXzuPadYstLVXxhg,7478
1488
1495
  mteb/models/model_implementations/facebookai.py,sha256=uhE6rB1YgxE0SIc7u8heE1U62qRFFA23IMgpjxBq_Ok,3116
1489
1496
  mteb/models/model_implementations/geogpt_models.py,sha256=Juv86SwhgQX80lVLjAFtim2aSiJT1AcgjniyyiKyk1Q,1923
1490
- mteb/models/model_implementations/gme_v_models.py,sha256=NkfgR3_UdZzoBt1NnalVou6LOR-F7qXM4by9EbAVrys,13568
1491
- mteb/models/model_implementations/google_models.py,sha256=7QfsaJ5JNDRQxFl7Zh2AtiR2PR7PZcfeCBgviuOFBCo,9130
1492
- mteb/models/model_implementations/granite_vision_embedding_models.py,sha256=uqQ5-e_a-ADv3gf3sR9Drk0S4x8Gy8mZkpL-E4X16TM,7241
1497
+ mteb/models/model_implementations/gme_v_models.py,sha256=GEu1wl5q77RMM3BwtKMjkMwm38KX_r0qWxD_IEMVC2U,13657
1498
+ mteb/models/model_implementations/google_models.py,sha256=d6hZ-yWY-yZnQsXDVbdtBb_xqwYAkdeeAnsEMaqqGXI,11013
1499
+ mteb/models/model_implementations/granite_vision_embedding_models.py,sha256=cvG5NliPwDVMvGuJTo8rk5yL3m6cuJZ_fMLEc0ESNfc,7315
1493
1500
  mteb/models/model_implementations/gritlm_models.py,sha256=aS_CuioL95JAQMYiaKlGuAWU9wZjabn268Xut3bD8-w,3005
1494
1501
  mteb/models/model_implementations/gte_models.py,sha256=o26Xyu_tucUlP435Q_jB4-bl0xckgj4wtbutTwhYgIo,10073
1495
1502
  mteb/models/model_implementations/hinvec_models.py,sha256=I_d_dSNVaGIwMIwyvTlaPAzGMpwh_PzvsfE4y47GFyg,1575
1496
1503
  mteb/models/model_implementations/human.py,sha256=klMpuMAtYH92EIEwNMEhne_Baf9fNiTg1DNWYD11P44,532
1497
1504
  mteb/models/model_implementations/ibm_granite_models.py,sha256=YCT0jbgawy19ps5l8QlxpQoJLjq8Nh-3R-e6yxS0DRM,7902
1498
1505
  mteb/models/model_implementations/inf_models.py,sha256=lvXUFhAYDltq2_Xa9MHcwfhh1V20rbJLSgON76tkj6w,2906
1499
- mteb/models/model_implementations/jasper_models.py,sha256=ZY7qRRpBpD3eVryQb4rLs5E3KDXlgFBvyelataqLIWs,16213
1506
+ mteb/models/model_implementations/jasper_models.py,sha256=onX_ipI-UZbaZrjcHpZtk34tpy6DcT6Yvq6X3RMSmYA,16211
1500
1507
  mteb/models/model_implementations/jina_clip.py,sha256=CfiIxbhKspjQajNtObCfGPHOWPk6uLn4cuwydQHFTMo,5118
1501
- mteb/models/model_implementations/jina_models.py,sha256=HrHm2Io3g9gHwxU5icAaudy_E8rAVkAAIFSzVYWF-dM,34859
1508
+ mteb/models/model_implementations/jina_models.py,sha256=1bkGwIaRNIun2ghkWb4FG-7js4lJ39s97Q9KAW3wkXo,34858
1502
1509
  mteb/models/model_implementations/kalm_models.py,sha256=FmW7Z5Qs6WYBLuKvql3u4IJW36kj4k-Ypah8qTBEBkg,59837
1503
1510
  mteb/models/model_implementations/kblab.py,sha256=DDh8gDEI6YPjS4_yGYWC4HatE0mFf7vhGDU83zzV7V0,866
1504
1511
  mteb/models/model_implementations/kennethenevoldsen_models.py,sha256=DF-9nmsewYO9ikZ0kV81ujKGr7Ot36-9iPoxN7KX2mY,2993
@@ -1515,14 +1522,15 @@ mteb/models/model_implementations/mdbr_models.py,sha256=B7R3dVEH9EZ_fSZ05VveSbmT
1515
1522
  mteb/models/model_implementations/misc_models.py,sha256=bgKOuXJC8cVQmVRXEfIBlgzxDRb9nzOCsHdJ1kM8Z2Q,56691
1516
1523
  mteb/models/model_implementations/mme5_models.py,sha256=cRRXecC8EHeLQiEd1nfCb1vt75x_CnG1s_9lYRrtyTA,1484
1517
1524
  mteb/models/model_implementations/moco_models.py,sha256=Kl0nBsqkG3crYoo5YulFq1fv97U0-IBWVFHN0UuO0lg,5483
1525
+ mteb/models/model_implementations/mod_models.py,sha256=KHVdZWmag0Yz_NLGDPUz4TgNbKjUYqKVXS_G_rL_5yU,6731
1518
1526
  mteb/models/model_implementations/model2vec_models.py,sha256=D-EY-6P-cKKunbgzk4DHzJL1ogpWYFhpHbTLb8qQjJw,13765
1519
1527
  mteb/models/model_implementations/moka_models.py,sha256=Y5do7Z4JyGxabYrjHhkBLqCKTQKotniS-f4kOgXJjag,4995
1520
1528
  mteb/models/model_implementations/mxbai_models.py,sha256=33ta2BnhvKYBUgE89wFgPNf-CnOb7ooumZvqHOvbZsA,3593
1521
1529
  mteb/models/model_implementations/nbailab.py,sha256=bqqR0qs10IH2g5HC6K962tDMBciw8qFsNVHADNS72jk,2396
1522
1530
  mteb/models/model_implementations/no_instruct_sentence_models.py,sha256=6i-xbLRRNKuDpU-hwklwdQjgu1wnz5CecLSoc6kyd7Q,3976
1523
- mteb/models/model_implementations/nomic_models.py,sha256=mT-v5Gs5-sRH8-ziCw_CtxB9ox3C6FtwWJjNghNrunw,11334
1524
- mteb/models/model_implementations/nomic_models_vision.py,sha256=gEEieMThvw4p-QhRH0G_9-WWTvj-jqOlgFsh6O07dbc,6731
1525
- mteb/models/model_implementations/nvidia_llama_nemoretriever_colemb.py,sha256=14XSv7wGsitu0cF8P3A951gel_Py7PrKlRixkLS4qG4,6203
1531
+ mteb/models/model_implementations/nomic_models.py,sha256=4N18fKKYXe8FGPqe4s5_6LV4rQsZad_2vAIOuxxwVeI,14417
1532
+ mteb/models/model_implementations/nomic_models_vision.py,sha256=6aca0XVLXnkGk6GW8jVCIbbjPGq98lKq4c9Az4jbEkE,6805
1533
+ mteb/models/model_implementations/nvidia_llama_nemoretriever_colemb.py,sha256=OEhVrvA-zfX2PSm76VcCDPkRyAArSFkVeweyLyzpqPI,6255
1526
1534
  mteb/models/model_implementations/nvidia_models.py,sha256=acVverAt77lURkILCVkCdXsWgY1BJoG1-ugB7yIhlIM,21555
1527
1535
  mteb/models/model_implementations/openai_models.py,sha256=loU6JByNUwRidq7lmcu8iGOtUQvzejw6HVLaF_IKCR0,9352
1528
1536
  mteb/models/model_implementations/openclip_models.py,sha256=W8XcokgLU1nSmMaWpYXkWWizVd3sQezcP02YtF2fXpo,11436
@@ -1532,12 +1540,12 @@ mteb/models/model_implementations/ordalietech_solon_embeddings_mini_beta_1_1.py,
1532
1540
  mteb/models/model_implementations/pawan_models.py,sha256=rV2ePGIuYroocvwqDXm4VU369Y_Vr67CyAE-08K5B9c,1151
1533
1541
  mteb/models/model_implementations/piccolo_models.py,sha256=d8Dtkv_ZTUOCmJLLOuwquq-gX-2UfKvAtl_LvAS0Xi0,2113
1534
1542
  mteb/models/model_implementations/promptriever_models.py,sha256=S7uWes_P74p3OZR_KBJHJN_ezlvvRx2__46DMCWqV5M,6328
1535
- mteb/models/model_implementations/pylate_models.py,sha256=yINGQL97S4xjj74-FTWpO4KHX-E9NDOEeyQWyRmmnaE,14772
1543
+ mteb/models/model_implementations/pylate_models.py,sha256=oNoPndZuiJahSd-ikR4dE4vL9261btXYiJbF3bk3Dco,14546
1536
1544
  mteb/models/model_implementations/qodo_models.py,sha256=JDqffDlQiOEariyheybOIf3iNkqot2gTkEIHWDnRbUE,2037
1537
1545
  mteb/models/model_implementations/qtack_models.py,sha256=biZLH5E3UWIcMZXIZNGgBZFEUvovPpAo6vUyL776W1w,1224
1538
1546
  mteb/models/model_implementations/qwen3_models.py,sha256=F_o6ciD-6gLFfIlQYD9MsNvcbkmGzJ39eKpFlEog1rM,5132
1539
1547
  mteb/models/model_implementations/qzhou_models.py,sha256=7KaZpHdap-YyK0QxOMHxU0W2aGismx7GZv_bNXkEOcI,3536
1540
- mteb/models/model_implementations/random_baseline.py,sha256=1VNnWBSi0Ph_RLON6clOuQI-Kli5BRtiiDFZMrTj7PM,7489
1548
+ mteb/models/model_implementations/random_baseline.py,sha256=z4xNs5fbH1HUZhtf3Ry5AKa264SWk2Y4eobRu8rmPKM,7563
1541
1549
  mteb/models/model_implementations/rasgaard_models.py,sha256=a8F3kDSBWHH0UR7wRioOrWGQUxtloD5mU7EG27iM-68,1260
1542
1550
  mteb/models/model_implementations/reasonir_model.py,sha256=wSCcJpUgZ0pG2g3vTEzYNmPlPG_CVn_rR0ENVCines0,2218
1543
1551
  mteb/models/model_implementations/repllama_models.py,sha256=89HoqEpzkNysHeuf_-YhU8WETamHTogSRztGIRo6G1s,7321
@@ -1550,7 +1558,7 @@ mteb/models/model_implementations/salesforce_models.py,sha256=KslTK-IKeLvNG-vQir
1550
1558
  mteb/models/model_implementations/samilpwc_models.py,sha256=oMwKNwCxoH1jZgCy04oo2oVlBZWu253QMpnEEC6emz8,2021
1551
1559
  mteb/models/model_implementations/sarashina_embedding_models.py,sha256=TSmr2FEX79mJTA9mbEV3meEZYSelGv58Veiw__TTGFM,8415
1552
1560
  mteb/models/model_implementations/searchmap_models.py,sha256=XvVl99emIgnNUCxkTuFQXW6py2R8vgsArfpyHveCugw,1904
1553
- mteb/models/model_implementations/seed_1_6_embedding_models.py,sha256=8J3htEddltyGTydIbnMUudgAV97FdD43-SQKaSA_Iuc,18534
1561
+ mteb/models/model_implementations/seed_1_6_embedding_models.py,sha256=Q8JTW2fjePR9dq4spuwK2lyVeL3mn1bl-H5wkQuEV_E,18609
1554
1562
  mteb/models/model_implementations/seed_models.py,sha256=SgK4kPVO6V33G3F1zSq06zSkWarPLEwBt1SWp4TUoVw,14142
1555
1563
  mteb/models/model_implementations/sentence_transformers_models.py,sha256=EtEaXg1yFFp3DQEOxu6am8bcVQR-ypcHj6DCqJGHOVU,21160
1556
1564
  mteb/models/model_implementations/shuu_model.py,sha256=KkcuVYjIzoha3Fvxh8ppqHQ9BfNMWeqDqn9dGCRKUjg,1167
@@ -1567,7 +1575,7 @@ mteb/models/model_implementations/vi_vn_models.py,sha256=quWmd3JT2J6SlAsFrV2gcnc
1567
1575
  mteb/models/model_implementations/vista_models.py,sha256=Q3I01kRtIPaoke0iMIcH4CLcCDTnMSIBFNCof7LPTX4,10832
1568
1576
  mteb/models/model_implementations/vlm2vec_models.py,sha256=HGGy_-z9Wc99xOKum71rBNipCPqWcM1efmmXgy5Rvxc,11724
1569
1577
  mteb/models/model_implementations/voyage_models.py,sha256=dOCccOQlloGrg0q44PxMQzx8dHuQ8VgkDUD01EydpJ0,19824
1570
- mteb/models/model_implementations/voyage_v.py,sha256=WnvwYNVv3c5K0ChzGA3v2iTQX2ekXYn_3402H721c6M,8088
1578
+ mteb/models/model_implementations/voyage_v.py,sha256=vT1MXCt6-_PWA9U7lNz-Qj2zyGHwm_79WqxH4elMm90,8162
1571
1579
  mteb/models/model_implementations/xyz_models.py,sha256=TePlrH6EHwRPO87U_J3Yce9-XHCn_X7I2cJ_6BZ2fUY,1296
1572
1580
  mteb/models/model_implementations/youtu_models.py,sha256=NB74E6z-_36HyXb8GXKn8CrmRLN68uX9eH4xcS57zl0,5938
1573
1581
  mteb/models/model_implementations/yuan_models.py,sha256=yZ6ki6YFaoVrJ_2pPSRQaMKOsIOUo3GtmhPx1qeUl2w,939
@@ -2120,9 +2128,11 @@ mteb/tasks/reranking/eng/web_linx_candidates_reranking.py,sha256=dGRRkf8GaPIAZAO
2120
2128
  mteb/tasks/reranking/fra/__init__.py,sha256=YhiXArWFZr_zxXFdKas0xkwxKrU45EbssiYF9c3D9FQ,148
2121
2129
  mteb/tasks/reranking/fra/alloprof_reranking.py,sha256=Evsf0YG2pJveP9qrXdJkRqNkfhGrKtXxGTEYfvk2bzU,1784
2122
2130
  mteb/tasks/reranking/fra/syntec_reranking.py,sha256=YqB1OPrcMDbfHEOrkCFd8W_Ve7Fm5b5ezY3FdT82Gd4,1290
2123
- mteb/tasks/reranking/jpn/__init__.py,sha256=RVT3hq_nzutfDCrI3c95oHWkQ2y1VS4XPRjX9CQ-AP0,220
2131
+ mteb/tasks/reranking/jpn/__init__.py,sha256=DBVF5VoKwnxZ0vcGaUEfrZUFz4zJjE9dG8L31Gv3Xg8,399
2124
2132
  mteb/tasks/reranking/jpn/j_qa_ra_reranking.py,sha256=8AhdHQSOzf0WgGCOXNhjG77RZjTtxMHrc1oBY38b13I,1648
2133
+ mteb/tasks/reranking/jpn/j_qa_ra_reranking_lite.py,sha256=RlX6Q4ie07UCAIlxhVmFqUTgSTt3a_H1edvMvXzw-Zk,1948
2125
2134
  mteb/tasks/reranking/jpn/ja_cwir_reranking.py,sha256=Us06popt1VSS5zoUUWfg52oTaX3F-6uUmCFYNIcs4i8,1630
2135
+ mteb/tasks/reranking/jpn/ja_cwir_reranking_lite.py,sha256=H9Y0u1O5icnnNJZnAFdMtVhEIS4VmYhkb4ctfFK9ULY,1904
2126
2136
  mteb/tasks/reranking/jpn/m_marco_reranking.py,sha256=T0kJC1u7OPem1Lg68czKzFb99C6dVpm115T8cg2vdAc,1392
2127
2137
  mteb/tasks/reranking/multilingual/__init__.py,sha256=xM-ZicCKPBtpfqkoeMGlhn76vLFOe49B1x27et42uQw,556
2128
2138
  mteb/tasks/reranking/multilingual/esci_reranking.py,sha256=opEtarEw8JhcqVhIZ2wQoFP0FFhXhKYXCsubFqM5BX0,1439
@@ -2156,7 +2166,7 @@ mteb/tasks/retrieval/code/code_trans_ocean_dl_retrieval.py,sha256=WrcLbhtJkGqWcs
2156
2166
  mteb/tasks/retrieval/code/coir_code_search_net_retrieval.py,sha256=HkRZbMlBa9jhRX7mil7zKAnT7yQna2yYH1UyAJE51EY,3785
2157
2167
  mteb/tasks/retrieval/code/cos_qa_retrieval.py,sha256=CYWty69H3aJQi3FHz-Qqj_O2usb19kH7Ct0nAcWNzlQ,1469
2158
2168
  mteb/tasks/retrieval/code/ds1000_retrieval.py,sha256=irbW7IN3a8NNkxSnWowBmlnilV7QRCbHp0fruRW8_Ic,3398
2159
- mteb/tasks/retrieval/code/fresh_stack_retrieval.py,sha256=th9gLiRICULGi4HGzjg2enw0ZkOhEYQpG5HruEk8hFw,3300
2169
+ mteb/tasks/retrieval/code/fresh_stack_retrieval.py,sha256=uoWHouYaDMbatauYFshabr7vH9jdiF8uraUcM5l0m9Q,3505
2160
2170
  mteb/tasks/retrieval/code/human_eval_retrieval.py,sha256=FagmoGdAjyh9hdIUxqjUbE-6QkSfvZTJ47oGQ3Vo_GE,4325
2161
2171
  mteb/tasks/retrieval/code/japanese_code1_retrieval.py,sha256=-FBDBmx2h4iYUv7b-jgwBXmHq7HguGpC6Uvc1fzbyb4,1133
2162
2172
  mteb/tasks/retrieval/code/mbpp_retrieval.py,sha256=EgNOypt5bfgy_-q2a4Sz-3x5CB9S2KGP_qxrWs6td5s,3350
@@ -2343,12 +2353,16 @@ mteb/tasks/retrieval/fra/french_legal1_retrieval.py,sha256=yq4avXuouedGq8y8WP4os
2343
2353
  mteb/tasks/retrieval/fra/syntec_retrieval.py,sha256=SZOm-z5OruxEG47zMYjApJoR2oWiHKsK5Vum41Z5hWU,2305
2344
2354
  mteb/tasks/retrieval/hun/__init__.py,sha256=M59LTpENxaFLMSU43mNiP38lChJ_l_yZh__1giKeUDc,93
2345
2355
  mteb/tasks/retrieval/hun/hun_sum2.py,sha256=td6lxYg_eH9J62sNNuFonHIJ_22E-XGgiFN-D3iAbFw,2373
2346
- mteb/tasks/retrieval/jpn/__init__.py,sha256=FJifPwzk9niyN16RyVr7aPr2T6K0GXSoASotX1PddeA,1175
2356
+ mteb/tasks/retrieval/jpn/__init__.py,sha256=1UA6fWOyaMieDBZxH9asudh9QLl20DW5alOGIdKDMAs,1519
2347
2357
  mteb/tasks/retrieval/jpn/ja_cwir_retrieval.py,sha256=x3rNQwi73WfpkYdGBwt24QccIWJRK_Zj9z16MUMyI3I,1603
2358
+ mteb/tasks/retrieval/jpn/ja_cwir_retrieval_lite.py,sha256=KXg08E250H_ueW3g8BYB-4elBaSAHt90eL4p8nDTIFo,1894
2348
2359
  mteb/tasks/retrieval/jpn/ja_gov_faqs_retrieval.py,sha256=_9zsw9QS53NFp2EiCw3BKQdfk57agHxkSfpzKNqdJXE,1170
2349
2360
  mteb/tasks/retrieval/jpn/ja_qu_ad_retrieval.py,sha256=qc89t-uJqzk37sTRKlSxenYOSq4Qy2E-H_namSBeGN0,1312
2350
2361
  mteb/tasks/retrieval/jpn/japanese_legal1_retrieval.py,sha256=drUYO9QMSWgxvYWxL5QBdYPZ35HNwCF2d0ju1yQlZrI,1121
2351
2362
  mteb/tasks/retrieval/jpn/jaqket_retrieval.py,sha256=dfSNx2QJ3bj5QZOHbGnInOxTlVXkgsFvYfMnmgU8PkE,1438
2363
+ mteb/tasks/retrieval/jpn/jaqket_retrieval_lite.py,sha256=HfSu6E_blhZxwzdprrA8r__vnNDur8IDMK6Kpa52XCw,2000
2364
+ mteb/tasks/retrieval/jpn/miracl_ja_retrieval_lite.py,sha256=uce4rZcmbyMq8q6K2UevKhW93wJzg5WGU-aTOgdzvUQ,2061
2365
+ mteb/tasks/retrieval/jpn/mr_tydi_ja_retrieval_lite.py,sha256=PHc3W8ftiDNhUCs8rfPDu6IYs8EzX6gp7OkXtfeFAKs,1819
2352
2366
  mteb/tasks/retrieval/jpn/nlp_journal_abs_article_retrieval.py,sha256=PyxSS9tab2drIQI6yEMUy4BxaoRGYNo8XySjp_xHkE8,3150
2353
2367
  mteb/tasks/retrieval/jpn/nlp_journal_abs_intro_retrieval.py,sha256=EEOQpTC6vEPULzC5_xDCt7r5LIL0K1zlExeqOC-G-E4,3068
2354
2368
  mteb/tasks/retrieval/jpn/nlp_journal_title_abs_retrieval.py,sha256=JOOW_5pRKHzVn8wTOY0fhxLJ6Ns7wlQHoGHGIYVovAQ,3056
@@ -2577,14 +2591,14 @@ mteb/tasks/zeroshot_classification/eng/sun397.py,sha256=Nls7tXM2Svu008MmAUjt-o_N
2577
2591
  mteb/tasks/zeroshot_classification/eng/ucf101.py,sha256=kwNRYks-_Oe4VE3GyoHIvN-2OJ6zhkwFr76WDNL9ymU,1884
2578
2592
  mteb/tasks/zeroshot_classification/eng/templates/__init__.py,sha256=da1PTClDMl-IBkrSvq6JC1lnS-K_BASzCvxVhNxN5Ls,13
2579
2593
  mteb/types/__init__.py,sha256=7_q6_84RvMuHeZK51GbLc5gbpTb3C1WmnqDHm6bnCzw,1104
2580
- mteb/types/_encoder_io.py,sha256=YlIthHwi0o-ObANsWwVPcQc4pA1wpiRwIewDjNTMAdQ,5461
2594
+ mteb/types/_encoder_io.py,sha256=Q7llxv3FfiExFKiQGHtATvbSk4_DwdJolLMPTnAPrrI,5536
2581
2595
  mteb/types/_metadata.py,sha256=NN-W0S6a5TDV7UkpRx1pyWtGF4TyyCyoPUfHOwdeci8,2290
2582
2596
  mteb/types/_result.py,sha256=CRAUc5IvqI3_9SyXDwv-PWLCXwXdZem9RePeYESRtuw,996
2583
2597
  mteb/types/_string_validators.py,sha256=PY-dYq4E8O50VS3bLYdldPWp400fl_WzUjfVSkNWe8U,523
2584
2598
  mteb/types/statistics.py,sha256=YwJsxTf1eaCI_RE-J37a-gK5wDeGAsmkeZKoZCFihSo,3755
2585
- mteb-2.3.10.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
2586
- mteb-2.3.10.dist-info/METADATA,sha256=IPpkXC-YeiZU0BtiAnv-e9aS8X99_uAsGYxCCIz7nr4,13924
2587
- mteb-2.3.10.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
2588
- mteb-2.3.10.dist-info/entry_points.txt,sha256=8IJoEJFKoDHmVnNev-qJ9pp4Ln7_1-ma9QsXnzVCzGU,39
2589
- mteb-2.3.10.dist-info/top_level.txt,sha256=OLVIjcQAlWBz0bdmutKlWHLF42FF0hp4uVAg3ZyiG4U,5
2590
- mteb-2.3.10.dist-info/RECORD,,
2599
+ mteb-2.4.1.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
2600
+ mteb-2.4.1.dist-info/METADATA,sha256=NSoqOepWRk38b5qA_3AUj6QzR66bca71Bcs7TxJx42o,13990
2601
+ mteb-2.4.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
2602
+ mteb-2.4.1.dist-info/entry_points.txt,sha256=8IJoEJFKoDHmVnNev-qJ9pp4Ln7_1-ma9QsXnzVCzGU,39
2603
+ mteb-2.4.1.dist-info/top_level.txt,sha256=OLVIjcQAlWBz0bdmutKlWHLF42FF0hp4uVAg3ZyiG4U,5
2604
+ mteb-2.4.1.dist-info/RECORD,,
File without changes