mteb 2.1.6__py3-none-any.whl → 2.1.8__py3-none-any.whl

mteb/tasks/sts/vie/sts_benchmark_stsvn.py

@@ -9,11 +9,7 @@ class STSBenchmarkSTSVN(AbsTaskSTS):
             "path": "GreenNode/stsbenchmark-sts-vn",
             "revision": "f24d66738cda4a02138ada5af7689a92ce1fcad6",
         },
-        description="""A translated dataset from Semantic Textual Similarity Benchmark (STSbenchmark) dataset.
-            The process of creating the VN-MTEB (Vietnamese Massive Text Embedding Benchmark) from English samples involves a new automated system:
-            - The system uses large language models (LLMs), specifically Coherence's Aya model, for translation.
-            - Applies advanced embedding models to filter the translations.
-            - Use LLM-as-a-judge to scoring the quality of the samples base on multiple criteria.""",
+        description="A translated dataset from Semantic Textual Similarity Benchmark (STSbenchmark) dataset. The process of creating the VN-MTEB (Vietnamese Massive Text Embedding Benchmark) from English samples involves a new automated system: - The system uses large language models (LLMs), specifically Coherence's Aya model, for translation. - Applies advanced embedding models to filter the translations. - Use LLM-as-a-judge to scoring the quality of the samples base on multiple criteria.",
         reference="https://github.com/PhilipMay/stsb-multi-mt/",
         type="STS",
         category="t2c",

mteb/tasks/zeroshot_classification/eng/gtsrb.py

@@ -9,7 +9,7 @@ from mteb.abstasks.zeroshot_classification import (
 class GTSRBZeroShotClassification(AbsTaskZeroShotClassification):
     metadata = TaskMetadata(
         name="GTSRBZeroShot",
-        description="""The German Traffic Sign Recognition Benchmark (GTSRB) is a multi-class classification dataset for traffic signs. It consists of dataset of more than 50,000 traffic sign images. The dataset comprises 43 classes with unbalanced class frequencies.""",
+        description="The German Traffic Sign Recognition Benchmark (GTSRB) is a multi-class classification dataset for traffic signs. It consists of dataset of more than 50,000 traffic sign images. The dataset comprises 43 classes with unbalanced class frequencies.",
         reference="https://benchmark.ini.rub.de/",
         dataset={
             "path": "clip-benchmark/wds_gtsrb",

mteb/tasks/zeroshot_classification/eng/patch_camelyon.py

@@ -9,7 +9,7 @@ from mteb.abstasks.zeroshot_classification import (
 class PatchCamelyonZeroShotClassification(AbsTaskZeroShotClassification):
     metadata = TaskMetadata(
         name="PatchCamelyonZeroShot",
-        description="""Histopathology diagnosis classification dataset.""",
+        description="Histopathology diagnosis classification dataset.",
         reference="https://link.springer.com/chapter/10.1007/978-3-030-00934-2_24",
         dataset={
             "path": "clip-benchmark/wds_vtab-pcam",

mteb/tasks/zeroshot_classification/eng/ucf101.py

@@ -7,11 +7,7 @@ from mteb.abstasks.zeroshot_classification import (
 class UCF101ZeroShotClassification(AbsTaskZeroShotClassification):
     metadata = TaskMetadata(
         name="UCF101ZeroShot",
-        description="""UCF101 is an action recognition data set of realistic
-action videos collected from YouTube, having 101 action categories. This
-version of the dataset does not contain images but images saved frame by
-frame. Train and test splits are generated based on the authors' first
-version train/test list.""",
+        description="UCF101 is an action recognition data set of realistic action videos collected from YouTube, having 101 action categories. This version of the dataset does not contain images but images saved frame by frame. Train and test splits are generated based on the authors' first version train/test list.",
         reference="https://huggingface.co/datasets/flwrlabs/ucf101",
         dataset={
             "path": "flwrlabs/ucf101",

{mteb-2.1.6.dist-info → mteb-2.1.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mteb
-Version: 2.1.6
+Version: 2.1.8
 Summary: Massive Text Embedding Benchmark
 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>
 Maintainer-email: Kenneth Enevoldsen <kenneth.enevoldsen@cas.au.dk>, Roman Solomatin <risolomatin@gmail.com>, Isaac Chung <chungisaac1217@gmail.com>