mteb 2.7.17__py3-none-any.whl → 2.7.19__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/_create_dataloaders.py +16 -16
- mteb/_evaluators/any_sts_evaluator.py +1 -1
- mteb/_evaluators/clustering_evaluator.py +1 -1
- mteb/_evaluators/image/imagetext_pairclassification_evaluator.py +2 -2
- mteb/_evaluators/pair_classification_evaluator.py +1 -1
- mteb/_evaluators/retrieval_evaluator.py +1 -1
- mteb/_evaluators/sklearn_evaluator.py +4 -2
- mteb/_evaluators/text/bitext_mining_evaluator.py +1 -1
- mteb/_evaluators/text/summarization_evaluator.py +1 -1
- mteb/_evaluators/zeroshot_classification_evaluator.py +1 -1
- mteb/abstasks/abstask.py +4 -4
- mteb/abstasks/classification.py +2 -2
- mteb/abstasks/clustering.py +1 -1
- mteb/abstasks/clustering_legacy.py +1 -1
- mteb/abstasks/image/image_text_pair_classification.py +1 -1
- mteb/abstasks/multilabel_classification.py +1 -1
- mteb/abstasks/pair_classification.py +1 -1
- mteb/abstasks/retrieval.py +8 -5
- mteb/abstasks/retrieval_dataset_loaders.py +27 -8
- mteb/abstasks/sts.py +1 -1
- mteb/abstasks/text/bitext_mining.py +2 -2
- mteb/abstasks/text/reranking.py +1 -1
- mteb/abstasks/text/summarization.py +1 -1
- mteb/abstasks/zeroshot_classification.py +1 -1
- mteb/evaluate.py +2 -2
- mteb/models/model_implementations/bm25.py +2 -2
- mteb/models/model_implementations/ict_time_and_querit_models.py +115 -0
- mteb/models/model_implementations/pylate_models.py +4 -4
- mteb/models/models_protocols.py +2 -2
- mteb/models/search_wrappers.py +4 -4
- mteb/tasks/bitext_mining/multilingual/bible_nlp_bitext_mining.py +1 -1
- mteb/tasks/bitext_mining/multilingual/flores_bitext_mining.py +1 -1
- mteb/tasks/bitext_mining/multilingual/in22_conv_bitext_mining.py +1 -1
- mteb/tasks/bitext_mining/multilingual/in22_gen_bitext_mining.py +1 -1
- mteb/tasks/bitext_mining/multilingual/ntrex_bitext_mining.py +1 -1
- mteb/tasks/bitext_mining/multilingual/roma_tales_bitext_mining.py +1 -1
- mteb/tasks/classification/ben/bengali_document_classification.py +2 -2
- mteb/tasks/classification/ces/czech_product_review_sentiment_classification.py +2 -2
- mteb/tasks/classification/ces/czech_so_me_sentiment_classification.py +1 -1
- mteb/tasks/classification/multilingual/hin_dialect_classification.py +1 -1
- mteb/tasks/classification/multilingual/indic_lang_classification.py +1 -1
- mteb/tasks/classification/multilingual/indic_sentiment_classification.py +1 -1
- mteb/tasks/classification/multilingual/language_classification.py +1 -1
- mteb/tasks/classification/multilingual/south_african_lang_classification.py +1 -1
- mteb/tasks/classification/multilingual/turkic_classification.py +1 -1
- mteb/tasks/classification/slk/slovak_movie_review_sentiment_classification.py +2 -2
- mteb/tasks/classification/swa/swahili_news_classification.py +2 -2
- mteb/tasks/clustering/deu/ten_k_gnad_clustering_p2p.py +1 -1
- mteb/tasks/clustering/deu/ten_k_gnad_clustering_s2s.py +1 -1
- mteb/tasks/clustering/multilingual/mlsum_clustering_p2p.py +2 -2
- mteb/tasks/clustering/multilingual/mlsum_clustering_s2s.py +2 -2
- mteb/tasks/clustering/nob/vg_hierarchical_clustering.py +2 -2
- mteb/tasks/image_text_pair_classification/eng/image_co_de.py +1 -1
- mteb/tasks/image_text_pair_classification/eng/sugar_crepe.py +1 -1
- mteb/tasks/instruction_reranking/multilingual/m_follow_ir.py +2 -2
- mteb/tasks/multichoice/eng/cv_bench.py +4 -4
- mteb/tasks/multilabel_classification/nld/covid_disinformation_nl_multi_label_classification.py +1 -1
- mteb/tasks/pair_classification/eng/pub_chem_smilespc.py +1 -1
- mteb/tasks/pair_classification/multilingual/pub_chem_wiki_pair_classification.py +1 -1
- mteb/tasks/pair_classification/multilingual/rte3.py +1 -1
- mteb/tasks/retrieval/ara/sadeem_question_retrieval.py +1 -1
- mteb/tasks/retrieval/code/code_edit_search_retrieval.py +1 -1
- mteb/tasks/retrieval/code/code_rag.py +8 -8
- mteb/tasks/retrieval/code/code_search_net_cc_retrieval.py +1 -1
- mteb/tasks/retrieval/code/coir_code_search_net_retrieval.py +1 -1
- mteb/tasks/retrieval/code/ds1000_retrieval.py +1 -1
- mteb/tasks/retrieval/code/fresh_stack_retrieval.py +1 -1
- mteb/tasks/retrieval/code/human_eval_retrieval.py +1 -1
- mteb/tasks/retrieval/code/mbpp_retrieval.py +1 -1
- mteb/tasks/retrieval/code/wiki_sql_retrieval.py +1 -1
- mteb/tasks/retrieval/dan/dan_fever_retrieval.py +2 -2
- mteb/tasks/retrieval/dan/tv2_nordretrieval.py +2 -2
- mteb/tasks/retrieval/dan/twitter_hjerne_retrieval.py +2 -2
- mteb/tasks/retrieval/deu/german_gov_service_retrieval.py +1 -1
- mteb/tasks/retrieval/deu/german_qu_ad_retrieval.py +1 -1
- mteb/tasks/retrieval/ell/greek_civics_qa.py +1 -1
- mteb/tasks/retrieval/eng/bright_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/chat_doctor_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/fin_qa_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/finance_bench_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/hateful_memes_i2t_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/hateful_memes_t2i_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/hc3_finance_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/lemb_narrative_qa_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/lemb_needle_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/lemb_passkey_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/lemb_summ_screen_fd_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/lemb_wikim_qa_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/lembqm_sum_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/lit_search_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/memotion_i2t_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/memotion_t2i_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/ml_questions.py +1 -1
- mteb/tasks/retrieval/eng/nano_argu_ana_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/nano_climate_fever_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/nano_db_pedia_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/nano_fever_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/nano_fi_qa2018_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/nano_hotpot_qa_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/nano_msmarco_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/nano_nf_corpus_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/nano_nq_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/nano_quora_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/nano_sci_fact_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/nano_scidocs_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/nano_touche2020_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/narrative_qa_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/r2_med_retrieval.py +8 -8
- mteb/tasks/retrieval/eng/sci_mmir_i2t_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/sci_mmir_t2i_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/vidore_bench_retrieval.py +10 -10
- mteb/tasks/retrieval/fra/f_qu_ad_retrieval.py +1 -1
- mteb/tasks/retrieval/fra/syntec_retrieval.py +1 -1
- mteb/tasks/retrieval/hun/hun_sum2.py +1 -1
- mteb/tasks/retrieval/kat/georgian_faq_retrieval.py +1 -1
- mteb/tasks/retrieval/multilingual/cross_lingual_semantic_discrimination_wmt19.py +1 -1
- mteb/tasks/retrieval/multilingual/cross_lingual_semantic_discrimination_wmt21.py +1 -1
- mteb/tasks/retrieval/multilingual/cur_ev1_retrieval.py +1 -1
- mteb/tasks/retrieval/multilingual/jina_vdr_bench_retrieval.py +1 -1
- mteb/tasks/retrieval/multilingual/miracl_vision_retrieval.py +1 -1
- mteb/tasks/retrieval/multilingual/mr_tidy_retrieval.py +1 -1
- mteb/tasks/retrieval/multilingual/public_health_qa_retrieval.py +1 -1
- mteb/tasks/retrieval/multilingual/ru_sci_bench_retrieval.py +2 -2
- mteb/tasks/retrieval/multilingual/statcan_dialogue_dataset_retrieval.py +1 -1
- mteb/tasks/retrieval/multilingual/vdr_multilingual_retrieval.py +1 -1
- mteb/tasks/retrieval/multilingual/vidore2_bench_retrieval.py +5 -5
- mteb/tasks/retrieval/multilingual/wit_t2i_retrieval.py +1 -1
- mteb/tasks/retrieval/multilingual/x_flickr30k_co_t2i_retrieval.py +1 -1
- mteb/tasks/retrieval/multilingual/x_qu_ad_retrieval.py +1 -1
- mteb/tasks/retrieval/multilingual/xm3600_t2i_retrieval.py +1 -1
- mteb/tasks/retrieval/nld/cqa_dupstack_android_nl_retrieval.py +1 -1
- mteb/tasks/retrieval/nld/cqa_dupstack_english_nl_retrieval.py +1 -1
- mteb/tasks/retrieval/nld/cqa_dupstack_gaming_nl_retrieval.py +1 -1
- mteb/tasks/retrieval/nld/cqa_dupstack_gis_nl_retrieval.py +1 -1
- mteb/tasks/retrieval/nld/cqa_dupstack_mathematica_nl_retrieval.py +1 -1
- mteb/tasks/retrieval/nld/cqa_dupstack_physics_nl_retrieval.py +1 -1
- mteb/tasks/retrieval/nld/cqa_dupstack_programmers_nl_retrieval.py +1 -1
- mteb/tasks/retrieval/nld/cqa_dupstack_stats_nl_retrieval.py +1 -1
- mteb/tasks/retrieval/nld/cqa_dupstack_tex_nl_retrieval.py +1 -1
- mteb/tasks/retrieval/nld/cqa_dupstack_unix_nl_retrieval.py +1 -1
- mteb/tasks/retrieval/nld/cqa_dupstack_webmasters_nl_retrieval.py +1 -1
- mteb/tasks/retrieval/nld/cqa_dupstack_wordpress_nl_retrieval.py +1 -1
- mteb/tasks/retrieval/nob/norquad.py +2 -2
- mteb/tasks/retrieval/nob/snl_retrieval.py +2 -2
- mteb/tasks/retrieval/slk/slovak_sum_retrieval.py +1 -1
- mteb/tasks/retrieval/vie/vie_qu_ad_retrieval.py +1 -1
- mteb/tasks/sts/multilingual/sem_rel24_sts.py +1 -1
- mteb/tasks/sts/multilingual/sts_benchmark_multilingual_sts.py +1 -1
- mteb/tasks/sts/por/assin2_sts.py +1 -1
- mteb/types/_encoder_io.py +1 -1
- {mteb-2.7.17.dist-info → mteb-2.7.19.dist-info}/METADATA +1 -1
- {mteb-2.7.17.dist-info → mteb-2.7.19.dist-info}/RECORD +156 -155
- {mteb-2.7.17.dist-info → mteb-2.7.19.dist-info}/WHEEL +0 -0
- {mteb-2.7.17.dist-info → mteb-2.7.19.dist-info}/entry_points.txt +0 -0
- {mteb-2.7.17.dist-info → mteb-2.7.19.dist-info}/licenses/LICENSE +0 -0
- {mteb-2.7.17.dist-info → mteb-2.7.19.dist-info}/top_level.txt +0 -0
|
@@ -51,7 +51,7 @@ class CodeRAGProgrammingSolutionsRetrieval(AbsTaskRetrieval):
|
|
|
51
51
|
**common_args,
|
|
52
52
|
)
|
|
53
53
|
|
|
54
|
-
def load_data(self, num_proc: int =
|
|
54
|
+
def load_data(self, num_proc: int | None = None, **kwargs) -> None:
|
|
55
55
|
"""Load dataset from HuggingFace hub"""
|
|
56
56
|
if self.data_loaded:
|
|
57
57
|
return
|
|
@@ -59,7 +59,7 @@ class CodeRAGProgrammingSolutionsRetrieval(AbsTaskRetrieval):
|
|
|
59
59
|
self.dataset_transform()
|
|
60
60
|
self.data_loaded = True
|
|
61
61
|
|
|
62
|
-
def dataset_transform(self, num_proc: int =
|
|
62
|
+
def dataset_transform(self, num_proc: int | None = None, **kwargs) -> None:
|
|
63
63
|
"""And transform to a retrieval dataset, which have the following attributes
|
|
64
64
|
|
|
65
65
|
self.corpus = Dict[doc_id, Dict[str, str]] #id => dict with document data like title and text
|
|
@@ -108,7 +108,7 @@ class CodeRAGOnlineTutorialsRetrieval(AbsTaskRetrieval):
|
|
|
108
108
|
**common_args,
|
|
109
109
|
)
|
|
110
110
|
|
|
111
|
-
def load_data(self, num_proc: int =
|
|
111
|
+
def load_data(self, num_proc: int | None = None, **kwargs) -> None:
|
|
112
112
|
"""Load dataset from HuggingFace hub"""
|
|
113
113
|
if self.data_loaded:
|
|
114
114
|
return
|
|
@@ -116,7 +116,7 @@ class CodeRAGOnlineTutorialsRetrieval(AbsTaskRetrieval):
|
|
|
116
116
|
self.dataset_transform()
|
|
117
117
|
self.data_loaded = True
|
|
118
118
|
|
|
119
|
-
def dataset_transform(self, num_proc: int =
|
|
119
|
+
def dataset_transform(self, num_proc: int | None = None, **kwargs) -> None:
|
|
120
120
|
"""And transform to a retrieval dataset, which have the following attributes
|
|
121
121
|
|
|
122
122
|
self.corpus = Dict[doc_id, Dict[str, str]] #id => dict with document data like title and text
|
|
@@ -168,7 +168,7 @@ class CodeRAGLibraryDocumentationSolutionsRetrieval(AbsTaskRetrieval):
|
|
|
168
168
|
**common_args,
|
|
169
169
|
)
|
|
170
170
|
|
|
171
|
-
def load_data(self, num_proc: int =
|
|
171
|
+
def load_data(self, num_proc: int | None = None, **kwargs) -> None:
|
|
172
172
|
"""Load dataset from HuggingFace hub"""
|
|
173
173
|
if self.data_loaded:
|
|
174
174
|
return
|
|
@@ -176,7 +176,7 @@ class CodeRAGLibraryDocumentationSolutionsRetrieval(AbsTaskRetrieval):
|
|
|
176
176
|
self.dataset_transform()
|
|
177
177
|
self.data_loaded = True
|
|
178
178
|
|
|
179
|
-
def dataset_transform(self, num_proc: int =
|
|
179
|
+
def dataset_transform(self, num_proc: int | None = None, **kwargs) -> None:
|
|
180
180
|
"""And transform to a retrieval dataset, which have the following attributes
|
|
181
181
|
|
|
182
182
|
self.corpus = Dict[doc_id, Dict[str, str]] #id => dict with document data like title and text
|
|
@@ -225,7 +225,7 @@ class CodeRAGStackoverflowPostsRetrieval(AbsTaskRetrieval):
|
|
|
225
225
|
**common_args,
|
|
226
226
|
)
|
|
227
227
|
|
|
228
|
-
def load_data(self, num_proc: int =
|
|
228
|
+
def load_data(self, num_proc: int | None = None, **kwargs) -> None:
|
|
229
229
|
"""Load dataset from HuggingFace hub"""
|
|
230
230
|
if self.data_loaded:
|
|
231
231
|
return
|
|
@@ -233,7 +233,7 @@ class CodeRAGStackoverflowPostsRetrieval(AbsTaskRetrieval):
|
|
|
233
233
|
self.dataset_transform()
|
|
234
234
|
self.data_loaded = True
|
|
235
235
|
|
|
236
|
-
def dataset_transform(self, num_proc: int =
|
|
236
|
+
def dataset_transform(self, num_proc: int | None = None, **kwargs) -> None:
|
|
237
237
|
"""And transform to a retrieval dataset, which have the following attributes
|
|
238
238
|
|
|
239
239
|
self.corpus = Dict[doc_id, Dict[str, str]] #id => dict with document data like title and text
|
|
@@ -47,7 +47,7 @@ Derczynski, Leon},
|
|
|
47
47
|
task_subtypes=["Claim verification"],
|
|
48
48
|
)
|
|
49
49
|
|
|
50
|
-
def load_data(self, num_proc: int =
|
|
50
|
+
def load_data(self, num_proc: int | None = None, **kwargs) -> None:
|
|
51
51
|
"""Load dataset from HuggingFace hub"""
|
|
52
52
|
if self.data_loaded:
|
|
53
53
|
return
|
|
@@ -55,7 +55,7 @@ Derczynski, Leon},
|
|
|
55
55
|
self.dataset_transform()
|
|
56
56
|
self.data_loaded = True
|
|
57
57
|
|
|
58
|
-
def dataset_transform(self, num_proc: int =
|
|
58
|
+
def dataset_transform(self, num_proc: int | None = None, **kwargs) -> None:
|
|
59
59
|
"""And transform to a retrieval dataset, which have the following attributes
|
|
60
60
|
|
|
61
61
|
self.corpus = dict[doc_id, dict[str, str]] #id => dict with document data like title and text
|
|
@@ -60,7 +60,7 @@ Piperidis, Stelios},
|
|
|
60
60
|
task_subtypes=["Article retrieval"],
|
|
61
61
|
)
|
|
62
62
|
|
|
63
|
-
def load_data(self, num_proc: int =
|
|
63
|
+
def load_data(self, num_proc: int | None = None, **kwargs) -> None:
|
|
64
64
|
"""Load dataset from HuggingFace hub"""
|
|
65
65
|
if self.data_loaded:
|
|
66
66
|
return
|
|
@@ -68,7 +68,7 @@ Piperidis, Stelios},
|
|
|
68
68
|
self.dataset_transform()
|
|
69
69
|
self.data_loaded = True
|
|
70
70
|
|
|
71
|
-
def dataset_transform(self, num_proc: int =
|
|
71
|
+
def dataset_transform(self, num_proc: int | None = None, **kwargs) -> None:
|
|
72
72
|
"""And transform to a retrieval dataset, which have the following attributes
|
|
73
73
|
|
|
74
74
|
self.corpus = dict[doc_id, dict[str, str]] #id => dict with document data like title and text
|
|
@@ -36,7 +36,7 @@ class TwitterHjerneRetrieval(AbsTaskRetrieval):
|
|
|
36
36
|
task_subtypes=["Question answering"],
|
|
37
37
|
)
|
|
38
38
|
|
|
39
|
-
def load_data(self, num_proc: int =
|
|
39
|
+
def load_data(self, num_proc: int | None = None, **kwargs) -> None:
|
|
40
40
|
"""Load dataset from HuggingFace hub"""
|
|
41
41
|
if self.data_loaded:
|
|
42
42
|
return
|
|
@@ -44,7 +44,7 @@ class TwitterHjerneRetrieval(AbsTaskRetrieval):
|
|
|
44
44
|
self.dataset_transform()
|
|
45
45
|
self.data_loaded = True
|
|
46
46
|
|
|
47
|
-
def dataset_transform(self, num_proc: int =
|
|
47
|
+
def dataset_transform(self, num_proc: int | None = None, **kwargs) -> None:
|
|
48
48
|
"""And transform to a retrieval dataset, which have the following attributes
|
|
49
49
|
|
|
50
50
|
self.corpus = dict[doc_id, dict[str, str]] #id => dict with document data like title and text
|
|
@@ -50,7 +50,7 @@ Lukas, Leon},
|
|
|
50
50
|
def get_hash(input_str) -> str:
|
|
51
51
|
return hashlib.md5(input_str.encode("utf-8")).hexdigest()
|
|
52
52
|
|
|
53
|
-
def load_data(self, num_proc: int =
|
|
53
|
+
def load_data(self, num_proc: int | None = None, **kwargs) -> None:
|
|
54
54
|
if self.data_loaded:
|
|
55
55
|
return
|
|
56
56
|
|
|
@@ -31,7 +31,7 @@ class GreekCivicsQA(AbsTaskRetrieval):
|
|
|
31
31
|
bibtex_citation="",
|
|
32
32
|
)
|
|
33
33
|
|
|
34
|
-
def load_data(self, num_proc: int =
|
|
34
|
+
def load_data(self, num_proc: int | None = None, **kwargs) -> None:
|
|
35
35
|
if self.data_loaded:
|
|
36
36
|
return
|
|
37
37
|
# fetch both subsets of the dataset
|
|
@@ -90,7 +90,7 @@ class HatefulMemesI2TRetrieval(AbsTaskRetrieval):
|
|
|
90
90
|
""",
|
|
91
91
|
)
|
|
92
92
|
|
|
93
|
-
def load_data(self, num_proc: int =
|
|
93
|
+
def load_data(self, num_proc: int | None = None, **kwargs) -> None:
|
|
94
94
|
if self.data_loaded:
|
|
95
95
|
return
|
|
96
96
|
self.corpus, self.queries, self.relevant_docs = _load_data(
|
|
@@ -90,7 +90,7 @@ class HatefulMemesT2IRetrieval(AbsTaskRetrieval):
|
|
|
90
90
|
""",
|
|
91
91
|
)
|
|
92
92
|
|
|
93
|
-
def load_data(self, num_proc: int =
|
|
93
|
+
def load_data(self, num_proc: int | None = None, **kwargs) -> None:
|
|
94
94
|
if self.data_loaded:
|
|
95
95
|
return
|
|
96
96
|
self.corpus, self.queries, self.relevant_docs = _load_data(
|
|
@@ -35,7 +35,7 @@ class LitSearchRetrieval(AbsTaskRetrieval):
|
|
|
35
35
|
""",
|
|
36
36
|
)
|
|
37
37
|
|
|
38
|
-
def load_data(self, num_proc: int =
|
|
38
|
+
def load_data(self, num_proc: int | None = None, **kwargs) -> None:
|
|
39
39
|
if self.data_loaded:
|
|
40
40
|
return
|
|
41
41
|
self.corpus, self.queries, self.relevant_docs = {}, {}, {}
|
|
@@ -113,7 +113,7 @@ class MemotionI2TRetrieval(AbsTaskRetrieval):
|
|
|
113
113
|
""",
|
|
114
114
|
)
|
|
115
115
|
|
|
116
|
-
def load_data(self, num_proc: int =
|
|
116
|
+
def load_data(self, num_proc: int | None = None, **kwargs) -> None:
|
|
117
117
|
if self.data_loaded:
|
|
118
118
|
return
|
|
119
119
|
self.corpus, self.queries, self.relevant_docs = _load_data(
|
|
@@ -112,7 +112,7 @@ class MemotionT2IRetrieval(AbsTaskRetrieval):
|
|
|
112
112
|
""",
|
|
113
113
|
)
|
|
114
114
|
|
|
115
|
-
def load_data(self, num_proc: int =
|
|
115
|
+
def load_data(self, num_proc: int | None = None, **kwargs) -> None:
|
|
116
116
|
if self.data_loaded:
|
|
117
117
|
return
|
|
118
118
|
self.corpus, self.queries, self.relevant_docs = _load_data(
|
|
@@ -44,7 +44,7 @@ class NanoClimateFeverRetrieval(AbsTaskRetrieval):
|
|
|
44
44
|
adapted_from=["ClimateFEVER"],
|
|
45
45
|
)
|
|
46
46
|
|
|
47
|
-
def load_data(self, num_proc: int =
|
|
47
|
+
def load_data(self, num_proc: int | None = None, **kwargs) -> None:
|
|
48
48
|
if self.data_loaded:
|
|
49
49
|
return
|
|
50
50
|
|
|
@@ -70,7 +70,7 @@ class R2MEDBiologyRetrieval(AbsTaskRetrieval):
|
|
|
70
70
|
""",
|
|
71
71
|
)
|
|
72
72
|
|
|
73
|
-
def load_data(self, num_proc: int =
|
|
73
|
+
def load_data(self, num_proc: int | None = None, **kwargs) -> None:
|
|
74
74
|
if self.data_loaded:
|
|
75
75
|
return
|
|
76
76
|
|
|
@@ -114,7 +114,7 @@ class R2MEDBioinformaticsRetrieval(AbsTaskRetrieval):
|
|
|
114
114
|
""",
|
|
115
115
|
)
|
|
116
116
|
|
|
117
|
-
def load_data(self, num_proc: int =
|
|
117
|
+
def load_data(self, num_proc: int | None = None, **kwargs) -> None:
|
|
118
118
|
if self.data_loaded:
|
|
119
119
|
return
|
|
120
120
|
|
|
@@ -158,7 +158,7 @@ class R2MEDMedicalSciencesRetrieval(AbsTaskRetrieval):
|
|
|
158
158
|
""",
|
|
159
159
|
)
|
|
160
160
|
|
|
161
|
-
def load_data(self, num_proc: int =
|
|
161
|
+
def load_data(self, num_proc: int | None = None, **kwargs) -> None:
|
|
162
162
|
if self.data_loaded:
|
|
163
163
|
return
|
|
164
164
|
|
|
@@ -202,7 +202,7 @@ class R2MEDMedXpertQAExamRetrieval(AbsTaskRetrieval):
|
|
|
202
202
|
""",
|
|
203
203
|
)
|
|
204
204
|
|
|
205
|
-
def load_data(self, num_proc: int =
|
|
205
|
+
def load_data(self, num_proc: int | None = None, **kwargs) -> None:
|
|
206
206
|
if self.data_loaded:
|
|
207
207
|
return
|
|
208
208
|
|
|
@@ -246,7 +246,7 @@ class R2MEDMedQADiagRetrieval(AbsTaskRetrieval):
|
|
|
246
246
|
""",
|
|
247
247
|
)
|
|
248
248
|
|
|
249
|
-
def load_data(self, num_proc: int =
|
|
249
|
+
def load_data(self, num_proc: int | None = None, **kwargs) -> None:
|
|
250
250
|
if self.data_loaded:
|
|
251
251
|
return
|
|
252
252
|
|
|
@@ -290,7 +290,7 @@ class R2MEDPMCTreatmentRetrieval(AbsTaskRetrieval):
|
|
|
290
290
|
""",
|
|
291
291
|
)
|
|
292
292
|
|
|
293
|
-
def load_data(self, num_proc: int =
|
|
293
|
+
def load_data(self, num_proc: int | None = None, **kwargs) -> None:
|
|
294
294
|
if self.data_loaded:
|
|
295
295
|
return
|
|
296
296
|
|
|
@@ -334,7 +334,7 @@ class R2MEDPMCClinicalRetrieval(AbsTaskRetrieval):
|
|
|
334
334
|
""",
|
|
335
335
|
)
|
|
336
336
|
|
|
337
|
-
def load_data(self, num_proc: int =
|
|
337
|
+
def load_data(self, num_proc: int | None = None, **kwargs) -> None:
|
|
338
338
|
if self.data_loaded:
|
|
339
339
|
return
|
|
340
340
|
|
|
@@ -378,7 +378,7 @@ class R2MEDIIYiClinicalRetrieval(AbsTaskRetrieval):
|
|
|
378
378
|
""",
|
|
379
379
|
)
|
|
380
380
|
|
|
381
|
-
def load_data(self, num_proc: int =
|
|
381
|
+
def load_data(self, num_proc: int | None = None, **kwargs) -> None:
|
|
382
382
|
if self.data_loaded:
|
|
383
383
|
return
|
|
384
384
|
|
|
@@ -88,7 +88,7 @@ class SciMMIRI2TRetrieval(AbsTaskRetrieval):
|
|
|
88
88
|
""",
|
|
89
89
|
)
|
|
90
90
|
|
|
91
|
-
def load_data(self, num_proc: int =
|
|
91
|
+
def load_data(self, num_proc: int | None = None, **kwargs) -> None:
|
|
92
92
|
if self.data_loaded:
|
|
93
93
|
return
|
|
94
94
|
self.corpus, self.queries, self.relevant_docs = _load_data(
|
|
@@ -88,7 +88,7 @@ class SciMMIRT2IRetrieval(AbsTaskRetrieval):
|
|
|
88
88
|
""",
|
|
89
89
|
)
|
|
90
90
|
|
|
91
|
-
def load_data(self, num_proc: int =
|
|
91
|
+
def load_data(self, num_proc: int | None = None, **kwargs) -> None:
|
|
92
92
|
if self.data_loaded:
|
|
93
93
|
return
|
|
94
94
|
self.corpus, self.queries, self.relevant_docs = _load_data(
|