From 607aac816893986a573ed988ec9dc532fec27e13 Mon Sep 17 00:00:00 2001
From: Roman Solomatin <36135455+Samoed@users.noreply.github.com>
Date: Thu, 2 Jan 2025 23:40:51 +0300
Subject: [PATCH 1/2] fix nano beir

---
 .../tasks/Retrieval/eng/NanoArguAnaRetrieval.py | 17 ++++++++++-------
 .../Retrieval/eng/NanoClimateFeverRetrieval.py  | 17 ++++++++++-------
 .../tasks/Retrieval/eng/NanoDBPediaRetrieval.py | 17 ++++++++++-------
 mteb/tasks/Retrieval/eng/NanoFEVERRetrieval.py  | 17 ++++++++++-------
 .../Retrieval/eng/NanoFiQA2018Retrieval.py      | 17 ++++++++++-------
 .../Retrieval/eng/NanoHotpotQARetrieval.py      | 17 ++++++++++-------
 .../tasks/Retrieval/eng/NanoMSMARCORetrieval.py | 17 ++++++++++-------
 .../Retrieval/eng/NanoNFCorpusRetrieval.py      | 17 ++++++++++-------
 mteb/tasks/Retrieval/eng/NanoNQRetrieval.py     | 16 +++++++++-------
 mteb/tasks/Retrieval/eng/NanoQuoraRetrieval.py  | 16 +++++++++-------
 .../tasks/Retrieval/eng/NanoSCIDOCSRetrieval.py | 17 ++++++++++-------
 .../tasks/Retrieval/eng/NanoSciFactRetrieval.py | 16 +++++++++-------
 .../Retrieval/eng/NanoTouche2020Retrieval.py    | 16 +++++++++-------
 13 files changed, 126 insertions(+), 91 deletions(-)

diff --git a/mteb/tasks/Retrieval/eng/NanoArguAnaRetrieval.py b/mteb/tasks/Retrieval/eng/NanoArguAnaRetrieval.py
index 2230368b94..e5dd1a8aa6 100644
--- a/mteb/tasks/Retrieval/eng/NanoArguAnaRetrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoArguAnaRetrieval.py
@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+from collections import defaultdict
+
 from datasets import load_dataset
 
 from mteb.abstasks.AbsTaskRetrieval import AbsTaskRetrieval
@@ -74,12 +76,13 @@ def load_data(self, **kwargs):
             for split in self.queries
         }
 
-        self.relevant_docs = {
-            split: {
-                sample["query-id"]: {sample["corpus-id"]: 1}
-                for sample in self.relevant_docs[split]
-            }
-            for split in self.relevant_docs
-        }
+        relevant_docs = {}
+
+        for split in self.relevant_docs:
+            relevant_docs[split] = defaultdict(dict)
+            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"],
+                                           self.relevant_docs[split]["corpus-id"]):
+                relevant_docs[split][query_id][corpus_id] = 1
+        self.relevant_docs = relevant_docs
 
         self.data_loaded = True
diff --git a/mteb/tasks/Retrieval/eng/NanoClimateFeverRetrieval.py b/mteb/tasks/Retrieval/eng/NanoClimateFeverRetrieval.py
index 0185a454d3..6aaf1e27bb 100644
--- a/mteb/tasks/Retrieval/eng/NanoClimateFeverRetrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoClimateFeverRetrieval.py
@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+from collections import defaultdict
+
 from datasets import load_dataset
 
 from mteb.abstasks.AbsTaskRetrieval import AbsTaskRetrieval
@@ -74,12 +76,13 @@ def load_data(self, **kwargs):
             for split in self.queries
         }
 
-        self.relevant_docs = {
-            split: {
-                sample["query-id"]: {sample["corpus-id"]: 1}
-                for sample in self.relevant_docs[split]
-            }
-            for split in self.relevant_docs
-        }
+        relevant_docs = {}
+
+        for split in self.relevant_docs:
+            relevant_docs[split] = defaultdict(dict)
+            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"],
+                                           self.relevant_docs[split]["corpus-id"]):
+                relevant_docs[split][query_id][corpus_id] = 1
+        self.relevant_docs = relevant_docs
 
         self.data_loaded = True
diff --git a/mteb/tasks/Retrieval/eng/NanoDBPediaRetrieval.py b/mteb/tasks/Retrieval/eng/NanoDBPediaRetrieval.py
index caa638743c..710b3a8706 100644
--- a/mteb/tasks/Retrieval/eng/NanoDBPediaRetrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoDBPediaRetrieval.py
@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+from collections import defaultdict
+
 from datasets import load_dataset
 
 from mteb.abstasks.AbsTaskRetrieval import AbsTaskRetrieval
@@ -64,12 +66,13 @@ def load_data(self, **kwargs):
             for split in self.queries
         }
 
-        self.relevant_docs = {
-            split: {
-                sample["query-id"]: {sample["corpus-id"]: 1}
-                for sample in self.relevant_docs[split]
-            }
-            for split in self.relevant_docs
-        }
+        relevant_docs = {}
+
+        for split in self.relevant_docs:
+            relevant_docs[split] = defaultdict(dict)
+            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"],
+                                           self.relevant_docs[split]["corpus-id"]):
+                relevant_docs[split][query_id][corpus_id] = 1
+        self.relevant_docs = relevant_docs
 
         self.data_loaded = True
diff --git a/mteb/tasks/Retrieval/eng/NanoFEVERRetrieval.py b/mteb/tasks/Retrieval/eng/NanoFEVERRetrieval.py
index 6bdd0ab4cf..221998861f 100644
--- a/mteb/tasks/Retrieval/eng/NanoFEVERRetrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoFEVERRetrieval.py
@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+from collections import defaultdict
+
 from datasets import load_dataset
 
 from mteb.abstasks.AbsTaskRetrieval import AbsTaskRetrieval
@@ -88,12 +90,13 @@ def load_data(self, **kwargs):
             for split in self.queries
         }
 
-        self.relevant_docs = {
-            split: {
-                sample["query-id"]: {sample["corpus-id"]: 1}
-                for sample in self.relevant_docs[split]
-            }
-            for split in self.relevant_docs
-        }
+        relevant_docs = {}
+
+        for split in self.relevant_docs:
+            relevant_docs[split] = defaultdict(dict)
+            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"],
+                                           self.relevant_docs[split]["corpus-id"]):
+                relevant_docs[split][query_id][corpus_id] = 1
+        self.relevant_docs = relevant_docs
 
         self.data_loaded = True
diff --git a/mteb/tasks/Retrieval/eng/NanoFiQA2018Retrieval.py b/mteb/tasks/Retrieval/eng/NanoFiQA2018Retrieval.py
index 1a3467c1d7..ea7e2b1cbb 100644
--- a/mteb/tasks/Retrieval/eng/NanoFiQA2018Retrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoFiQA2018Retrieval.py
@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+from collections import defaultdict
+
 from datasets import load_dataset
 
 from mteb.abstasks.AbsTaskRetrieval import AbsTaskRetrieval
@@ -74,12 +76,13 @@ def load_data(self, **kwargs):
             for split in self.queries
         }
 
-        self.relevant_docs = {
-            split: {
-                sample["query-id"]: {sample["corpus-id"]: 1}
-                for sample in self.relevant_docs[split]
-            }
-            for split in self.relevant_docs
-        }
+        relevant_docs = {}
+
+        for split in self.relevant_docs:
+            relevant_docs[split] = defaultdict(dict)
+            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"],
+                                           self.relevant_docs[split]["corpus-id"]):
+                relevant_docs[split][query_id][corpus_id] = 1
+        self.relevant_docs = relevant_docs
 
         self.data_loaded = True
diff --git a/mteb/tasks/Retrieval/eng/NanoHotpotQARetrieval.py b/mteb/tasks/Retrieval/eng/NanoHotpotQARetrieval.py
index 4389aeafa8..2a646f44c2 100644
--- a/mteb/tasks/Retrieval/eng/NanoHotpotQARetrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoHotpotQARetrieval.py
@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+from collections import defaultdict
+
 from datasets import load_dataset
 
 from mteb.abstasks.AbsTaskRetrieval import AbsTaskRetrieval
@@ -91,12 +93,13 @@ def load_data(self, **kwargs):
             for split in self.queries
         }
 
-        self.relevant_docs = {
-            split: {
-                sample["query-id"]: {sample["corpus-id"]: 1}
-                for sample in self.relevant_docs[split]
-            }
-            for split in self.relevant_docs
-        }
+        relevant_docs = {}
+
+        for split in self.relevant_docs:
+            relevant_docs[split] = defaultdict(dict)
+            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"],
+                                           self.relevant_docs[split]["corpus-id"]):
+                relevant_docs[split][query_id][corpus_id] = 1
+        self.relevant_docs = relevant_docs
 
         self.data_loaded = True
diff --git a/mteb/tasks/Retrieval/eng/NanoMSMARCORetrieval.py b/mteb/tasks/Retrieval/eng/NanoMSMARCORetrieval.py
index 8a2f51e7fd..89019a9803 100644
--- a/mteb/tasks/Retrieval/eng/NanoMSMARCORetrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoMSMARCORetrieval.py
@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+from collections import defaultdict
+
 from datasets import load_dataset
 
 from mteb.abstasks.AbsTaskRetrieval import AbsTaskRetrieval
@@ -86,12 +88,13 @@ def load_data(self, **kwargs):
             for split in self.queries
         }
 
-        self.relevant_docs = {
-            split: {
-                sample["query-id"]: {sample["corpus-id"]: 1}
-                for sample in self.relevant_docs[split]
-            }
-            for split in self.relevant_docs
-        }
+        relevant_docs = {}
+
+        for split in self.relevant_docs:
+            relevant_docs[split] = defaultdict(dict)
+            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"],
+                                           self.relevant_docs[split]["corpus-id"]):
+                relevant_docs[split][query_id][corpus_id] = 1
+        self.relevant_docs = relevant_docs
 
         self.data_loaded = True
diff --git a/mteb/tasks/Retrieval/eng/NanoNFCorpusRetrieval.py b/mteb/tasks/Retrieval/eng/NanoNFCorpusRetrieval.py
index 0f6ac8533a..d5d4ba8e75 100644
--- a/mteb/tasks/Retrieval/eng/NanoNFCorpusRetrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoNFCorpusRetrieval.py
@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+from collections import defaultdict
+
 from datasets import load_dataset
 
 from mteb.abstasks.AbsTaskRetrieval import AbsTaskRetrieval
@@ -76,12 +78,13 @@ def load_data(self, **kwargs):
             for split in self.queries
         }
 
-        self.relevant_docs = {
-            split: {
-                sample["query-id"]: {sample["corpus-id"]: 1}
-                for sample in self.relevant_docs[split]
-            }
-            for split in self.relevant_docs
-        }
+        relevant_docs = {}
+
+        for split in self.relevant_docs:
+            relevant_docs[split] = defaultdict(dict)
+            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"],
+                                           self.relevant_docs[split]["corpus-id"]):
+                relevant_docs[split][query_id][corpus_id] = 1
+        self.relevant_docs = relevant_docs
 
         self.data_loaded = True
diff --git a/mteb/tasks/Retrieval/eng/NanoNQRetrieval.py b/mteb/tasks/Retrieval/eng/NanoNQRetrieval.py
index 5aa831f799..536e5a0d93 100644
--- a/mteb/tasks/Retrieval/eng/NanoNQRetrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoNQRetrieval.py
@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+from collections import defaultdict
+
 from datasets import load_dataset
 
 from mteb.abstasks.AbsTaskRetrieval import AbsTaskRetrieval
@@ -72,12 +74,12 @@ def load_data(self, **kwargs):
             for split in self.queries
         }
 
-        self.relevant_docs = {
-            split: {
-                sample["query-id"]: {sample["corpus-id"]: 1}
-                for sample in self.relevant_docs[split]
-            }
-            for split in self.relevant_docs
-        }
+        relevant_docs = {}
+
+        for split in self.relevant_docs:
+            relevant_docs[split] = defaultdict(dict)
+            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"], self.relevant_docs[split]["corpus-id"]):
+                relevant_docs[split][query_id][corpus_id] = 1
+        self.relevant_docs = relevant_docs
 
         self.data_loaded = True
diff --git a/mteb/tasks/Retrieval/eng/NanoQuoraRetrieval.py b/mteb/tasks/Retrieval/eng/NanoQuoraRetrieval.py
index 1391d12b93..2c21fb1a6e 100644
--- a/mteb/tasks/Retrieval/eng/NanoQuoraRetrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoQuoraRetrieval.py
@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+from collections import defaultdict
+
 from datasets import load_dataset
 
 from mteb.abstasks.AbsTaskRetrieval import AbsTaskRetrieval
@@ -75,12 +77,12 @@ def load_data(self, **kwargs):
             for split in self.queries
         }
 
-        self.relevant_docs = {
-            split: {
-                sample["query-id"]: {sample["corpus-id"]: 1}
-                for sample in self.relevant_docs[split]
-            }
-            for split in self.relevant_docs
-        }
+        relevant_docs = {}
+
+        for split in self.relevant_docs:
+            relevant_docs[split] = defaultdict(dict)
+            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"], self.relevant_docs[split]["corpus-id"]):
+                relevant_docs[split][query_id][corpus_id] = 1
+        self.relevant_docs = relevant_docs
 
         self.data_loaded = True
diff --git a/mteb/tasks/Retrieval/eng/NanoSCIDOCSRetrieval.py b/mteb/tasks/Retrieval/eng/NanoSCIDOCSRetrieval.py
index 2d27e1a2dc..670decacb5 100644
--- a/mteb/tasks/Retrieval/eng/NanoSCIDOCSRetrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoSCIDOCSRetrieval.py
@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+from collections import defaultdict
+
 from datasets import load_dataset
 
 from mteb.abstasks.AbsTaskRetrieval import AbsTaskRetrieval
@@ -74,12 +76,13 @@ def load_data(self, **kwargs):
             for split in self.queries
         }
 
-        self.relevant_docs = {
-            split: {
-                sample["query-id"]: {sample["corpus-id"]: 1}
-                for sample in self.relevant_docs[split]
-            }
-            for split in self.relevant_docs
-        }
+        relevant_docs = {}
+
+        for split in self.relevant_docs:
+            relevant_docs[split] = defaultdict(dict)
+            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"],
+                                           self.relevant_docs[split]["corpus-id"]):
+                relevant_docs[split][query_id][corpus_id] = 1
+        self.relevant_docs = relevant_docs
 
         self.data_loaded = True
diff --git a/mteb/tasks/Retrieval/eng/NanoSciFactRetrieval.py b/mteb/tasks/Retrieval/eng/NanoSciFactRetrieval.py
index aff949d319..b921562c86 100644
--- a/mteb/tasks/Retrieval/eng/NanoSciFactRetrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoSciFactRetrieval.py
@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+from collections import defaultdict
+
 from datasets import load_dataset
 
 from mteb.abstasks.AbsTaskRetrieval import AbsTaskRetrieval
@@ -72,12 +74,12 @@ def load_data(self, **kwargs):
             for split in self.queries
         }
 
-        self.relevant_docs = {
-            split: {
-                sample["query-id"]: {sample["corpus-id"]: 1}
-                for sample in self.relevant_docs[split]
-            }
-            for split in self.relevant_docs
-        }
+        relevant_docs = {}
+
+        for split in self.relevant_docs:
+            relevant_docs[split] = defaultdict(dict)
+            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"], self.relevant_docs[split]["corpus-id"]):
+                relevant_docs[split][query_id][corpus_id] = 1
+        self.relevant_docs = relevant_docs
 
         self.data_loaded = True
diff --git a/mteb/tasks/Retrieval/eng/NanoTouche2020Retrieval.py b/mteb/tasks/Retrieval/eng/NanoTouche2020Retrieval.py
index 656b5494a0..f301a9d9e5 100644
--- a/mteb/tasks/Retrieval/eng/NanoTouche2020Retrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoTouche2020Retrieval.py
@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+from collections import defaultdict
+
 from datasets import load_dataset
 
 from mteb.abstasks.AbsTaskRetrieval import AbsTaskRetrieval
@@ -83,12 +85,12 @@ def load_data(self, **kwargs):
             for split in self.queries
         }
 
-        self.relevant_docs = {
-            split: {
-                sample["query-id"]: {sample["corpus-id"]: 1}
-                for sample in self.relevant_docs[split]
-            }
-            for split in self.relevant_docs
-        }
+        relevant_docs = {}
+
+        for split in self.relevant_docs:
+            relevant_docs[split] = defaultdict(dict)
+            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"], self.relevant_docs[split]["corpus-id"]):
+                relevant_docs[split][query_id][corpus_id] = 1
+        self.relevant_docs = relevant_docs
 
         self.data_loaded = True

From 6aa41e8fadc74677d5b206f5895606a91348e5d5 Mon Sep 17 00:00:00 2001
From: Roman Solomatin <36135455+Samoed@users.noreply.github.com>
Date: Thu, 2 Jan 2025 23:42:45 +0300
Subject: [PATCH 2/2] lint

---
 mteb/tasks/Retrieval/eng/NanoArguAnaRetrieval.py      | 6 ++++--
 mteb/tasks/Retrieval/eng/NanoClimateFeverRetrieval.py | 6 ++++--
 mteb/tasks/Retrieval/eng/NanoDBPediaRetrieval.py      | 6 ++++--
 mteb/tasks/Retrieval/eng/NanoFEVERRetrieval.py        | 6 ++++--
 mteb/tasks/Retrieval/eng/NanoFiQA2018Retrieval.py     | 6 ++++--
 mteb/tasks/Retrieval/eng/NanoHotpotQARetrieval.py     | 6 ++++--
 mteb/tasks/Retrieval/eng/NanoMSMARCORetrieval.py      | 6 ++++--
 mteb/tasks/Retrieval/eng/NanoNFCorpusRetrieval.py     | 6 ++++--
 mteb/tasks/Retrieval/eng/NanoNQRetrieval.py           | 5 ++++-
 mteb/tasks/Retrieval/eng/NanoQuoraRetrieval.py        | 5 ++++-
 mteb/tasks/Retrieval/eng/NanoSCIDOCSRetrieval.py      | 6 ++++--
 mteb/tasks/Retrieval/eng/NanoSciFactRetrieval.py      | 5 ++++-
 mteb/tasks/Retrieval/eng/NanoTouche2020Retrieval.py   | 5 ++++-
 13 files changed, 52 insertions(+), 22 deletions(-)

diff --git a/mteb/tasks/Retrieval/eng/NanoArguAnaRetrieval.py b/mteb/tasks/Retrieval/eng/NanoArguAnaRetrieval.py
index e5dd1a8aa6..7b5a728537 100644
--- a/mteb/tasks/Retrieval/eng/NanoArguAnaRetrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoArguAnaRetrieval.py
@@ -80,8 +80,10 @@ def load_data(self, **kwargs):
 
         for split in self.relevant_docs:
             relevant_docs[split] = defaultdict(dict)
-            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"],
-                                           self.relevant_docs[split]["corpus-id"]):
+            for query_id, corpus_id in zip(
+                self.relevant_docs[split]["query-id"],
+                self.relevant_docs[split]["corpus-id"],
+            ):
                 relevant_docs[split][query_id][corpus_id] = 1
         self.relevant_docs = relevant_docs
 
diff --git a/mteb/tasks/Retrieval/eng/NanoClimateFeverRetrieval.py b/mteb/tasks/Retrieval/eng/NanoClimateFeverRetrieval.py
index 6aaf1e27bb..b297dec5e3 100644
--- a/mteb/tasks/Retrieval/eng/NanoClimateFeverRetrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoClimateFeverRetrieval.py
@@ -80,8 +80,10 @@ def load_data(self, **kwargs):
 
         for split in self.relevant_docs:
             relevant_docs[split] = defaultdict(dict)
-            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"],
-                                           self.relevant_docs[split]["corpus-id"]):
+            for query_id, corpus_id in zip(
+                self.relevant_docs[split]["query-id"],
+                self.relevant_docs[split]["corpus-id"],
+            ):
                 relevant_docs[split][query_id][corpus_id] = 1
         self.relevant_docs = relevant_docs
 
diff --git a/mteb/tasks/Retrieval/eng/NanoDBPediaRetrieval.py b/mteb/tasks/Retrieval/eng/NanoDBPediaRetrieval.py
index 710b3a8706..37826697be 100644
--- a/mteb/tasks/Retrieval/eng/NanoDBPediaRetrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoDBPediaRetrieval.py
@@ -70,8 +70,10 @@ def load_data(self, **kwargs):
 
         for split in self.relevant_docs:
             relevant_docs[split] = defaultdict(dict)
-            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"],
-                                           self.relevant_docs[split]["corpus-id"]):
+            for query_id, corpus_id in zip(
+                self.relevant_docs[split]["query-id"],
+                self.relevant_docs[split]["corpus-id"],
+            ):
                 relevant_docs[split][query_id][corpus_id] = 1
         self.relevant_docs = relevant_docs
 
diff --git a/mteb/tasks/Retrieval/eng/NanoFEVERRetrieval.py b/mteb/tasks/Retrieval/eng/NanoFEVERRetrieval.py
index 221998861f..636bfd12a1 100644
--- a/mteb/tasks/Retrieval/eng/NanoFEVERRetrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoFEVERRetrieval.py
@@ -94,8 +94,10 @@ def load_data(self, **kwargs):
 
         for split in self.relevant_docs:
             relevant_docs[split] = defaultdict(dict)
-            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"],
-                                           self.relevant_docs[split]["corpus-id"]):
+            for query_id, corpus_id in zip(
+                self.relevant_docs[split]["query-id"],
+                self.relevant_docs[split]["corpus-id"],
+            ):
                 relevant_docs[split][query_id][corpus_id] = 1
         self.relevant_docs = relevant_docs
 
diff --git a/mteb/tasks/Retrieval/eng/NanoFiQA2018Retrieval.py b/mteb/tasks/Retrieval/eng/NanoFiQA2018Retrieval.py
index ea7e2b1cbb..4129a18137 100644
--- a/mteb/tasks/Retrieval/eng/NanoFiQA2018Retrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoFiQA2018Retrieval.py
@@ -80,8 +80,10 @@ def load_data(self, **kwargs):
 
         for split in self.relevant_docs:
             relevant_docs[split] = defaultdict(dict)
-            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"],
-                                           self.relevant_docs[split]["corpus-id"]):
+            for query_id, corpus_id in zip(
+                self.relevant_docs[split]["query-id"],
+                self.relevant_docs[split]["corpus-id"],
+            ):
                 relevant_docs[split][query_id][corpus_id] = 1
         self.relevant_docs = relevant_docs
 
diff --git a/mteb/tasks/Retrieval/eng/NanoHotpotQARetrieval.py b/mteb/tasks/Retrieval/eng/NanoHotpotQARetrieval.py
index 2a646f44c2..6c5a0a1b1d 100644
--- a/mteb/tasks/Retrieval/eng/NanoHotpotQARetrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoHotpotQARetrieval.py
@@ -97,8 +97,10 @@ def load_data(self, **kwargs):
 
         for split in self.relevant_docs:
             relevant_docs[split] = defaultdict(dict)
-            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"],
-                                           self.relevant_docs[split]["corpus-id"]):
+            for query_id, corpus_id in zip(
+                self.relevant_docs[split]["query-id"],
+                self.relevant_docs[split]["corpus-id"],
+            ):
                 relevant_docs[split][query_id][corpus_id] = 1
         self.relevant_docs = relevant_docs
 
diff --git a/mteb/tasks/Retrieval/eng/NanoMSMARCORetrieval.py b/mteb/tasks/Retrieval/eng/NanoMSMARCORetrieval.py
index 89019a9803..c603e2cc5b 100644
--- a/mteb/tasks/Retrieval/eng/NanoMSMARCORetrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoMSMARCORetrieval.py
@@ -92,8 +92,10 @@ def load_data(self, **kwargs):
 
         for split in self.relevant_docs:
             relevant_docs[split] = defaultdict(dict)
-            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"],
-                                           self.relevant_docs[split]["corpus-id"]):
+            for query_id, corpus_id in zip(
+                self.relevant_docs[split]["query-id"],
+                self.relevant_docs[split]["corpus-id"],
+            ):
                 relevant_docs[split][query_id][corpus_id] = 1
         self.relevant_docs = relevant_docs
 
diff --git a/mteb/tasks/Retrieval/eng/NanoNFCorpusRetrieval.py b/mteb/tasks/Retrieval/eng/NanoNFCorpusRetrieval.py
index d5d4ba8e75..725c7e889c 100644
--- a/mteb/tasks/Retrieval/eng/NanoNFCorpusRetrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoNFCorpusRetrieval.py
@@ -82,8 +82,10 @@ def load_data(self, **kwargs):
 
         for split in self.relevant_docs:
             relevant_docs[split] = defaultdict(dict)
-            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"],
-                                           self.relevant_docs[split]["corpus-id"]):
+            for query_id, corpus_id in zip(
+                self.relevant_docs[split]["query-id"],
+                self.relevant_docs[split]["corpus-id"],
+            ):
                 relevant_docs[split][query_id][corpus_id] = 1
         self.relevant_docs = relevant_docs
 
diff --git a/mteb/tasks/Retrieval/eng/NanoNQRetrieval.py b/mteb/tasks/Retrieval/eng/NanoNQRetrieval.py
index 536e5a0d93..538a0881fa 100644
--- a/mteb/tasks/Retrieval/eng/NanoNQRetrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoNQRetrieval.py
@@ -78,7 +78,10 @@ def load_data(self, **kwargs):
 
         for split in self.relevant_docs:
             relevant_docs[split] = defaultdict(dict)
-            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"], self.relevant_docs[split]["corpus-id"]):
+            for query_id, corpus_id in zip(
+                self.relevant_docs[split]["query-id"],
+                self.relevant_docs[split]["corpus-id"],
+            ):
                 relevant_docs[split][query_id][corpus_id] = 1
         self.relevant_docs = relevant_docs
 
diff --git a/mteb/tasks/Retrieval/eng/NanoQuoraRetrieval.py b/mteb/tasks/Retrieval/eng/NanoQuoraRetrieval.py
index 2c21fb1a6e..ac527acba2 100644
--- a/mteb/tasks/Retrieval/eng/NanoQuoraRetrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoQuoraRetrieval.py
@@ -81,7 +81,10 @@ def load_data(self, **kwargs):
 
         for split in self.relevant_docs:
             relevant_docs[split] = defaultdict(dict)
-            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"], self.relevant_docs[split]["corpus-id"]):
+            for query_id, corpus_id in zip(
+                self.relevant_docs[split]["query-id"],
+                self.relevant_docs[split]["corpus-id"],
+            ):
                 relevant_docs[split][query_id][corpus_id] = 1
         self.relevant_docs = relevant_docs
 
diff --git a/mteb/tasks/Retrieval/eng/NanoSCIDOCSRetrieval.py b/mteb/tasks/Retrieval/eng/NanoSCIDOCSRetrieval.py
index 670decacb5..f521d693d0 100644
--- a/mteb/tasks/Retrieval/eng/NanoSCIDOCSRetrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoSCIDOCSRetrieval.py
@@ -80,8 +80,10 @@ def load_data(self, **kwargs):
 
         for split in self.relevant_docs:
             relevant_docs[split] = defaultdict(dict)
-            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"],
-                                           self.relevant_docs[split]["corpus-id"]):
+            for query_id, corpus_id in zip(
+                self.relevant_docs[split]["query-id"],
+                self.relevant_docs[split]["corpus-id"],
+            ):
                 relevant_docs[split][query_id][corpus_id] = 1
         self.relevant_docs = relevant_docs
 
diff --git a/mteb/tasks/Retrieval/eng/NanoSciFactRetrieval.py b/mteb/tasks/Retrieval/eng/NanoSciFactRetrieval.py
index b921562c86..a24fa4e102 100644
--- a/mteb/tasks/Retrieval/eng/NanoSciFactRetrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoSciFactRetrieval.py
@@ -78,7 +78,10 @@ def load_data(self, **kwargs):
 
         for split in self.relevant_docs:
             relevant_docs[split] = defaultdict(dict)
-            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"], self.relevant_docs[split]["corpus-id"]):
+            for query_id, corpus_id in zip(
+                self.relevant_docs[split]["query-id"],
+                self.relevant_docs[split]["corpus-id"],
+            ):
                 relevant_docs[split][query_id][corpus_id] = 1
         self.relevant_docs = relevant_docs
 
diff --git a/mteb/tasks/Retrieval/eng/NanoTouche2020Retrieval.py b/mteb/tasks/Retrieval/eng/NanoTouche2020Retrieval.py
index f301a9d9e5..b5fccbedf6 100644
--- a/mteb/tasks/Retrieval/eng/NanoTouche2020Retrieval.py
+++ b/mteb/tasks/Retrieval/eng/NanoTouche2020Retrieval.py
@@ -89,7 +89,10 @@ def load_data(self, **kwargs):
 
         for split in self.relevant_docs:
             relevant_docs[split] = defaultdict(dict)
-            for query_id, corpus_id in zip(self.relevant_docs[split]["query-id"], self.relevant_docs[split]["corpus-id"]):
+            for query_id, corpus_id in zip(
+                self.relevant_docs[split]["query-id"],
+                self.relevant_docs[split]["corpus-id"],
+            ):
                 relevant_docs[split][query_id][corpus_id] = 1
         self.relevant_docs = relevant_docs