evalscope 0.5.4__tar.gz → 0.5.5rc1__tar.gz

{evalscope-0.5.4 → evalscope-0.5.5rc1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: evalscope
-Version: 0.5.4
+Version: 0.5.5rc1
 Summary: EvalScope: Lightweight LLMs Evaluation Framework
 Home-page: https://github.com/modelscope/evalscope
 Author: ModelScope team
@@ -48,7 +48,7 @@ Requires-Dist: transformers_stream_generator
 Requires-Dist: jieba
 Requires-Dist: rouge-chinese
 Provides-Extra: opencompass
-Requires-Dist: ms-opencompass>=0.1.0; extra == "opencompass"
+Requires-Dist: ms-opencompass>=0.1.1; extra == "opencompass"
 Provides-Extra: vlmeval
 Requires-Dist: ms-vlmeval>=0.0.5; extra == "vlmeval"
 Provides-Extra: inner
@@ -111,7 +111,7 @@ Requires-Dist: transformers>=4.33; extra == "all"
 Requires-Dist: transformers_stream_generator; extra == "all"
 Requires-Dist: jieba; extra == "all"
 Requires-Dist: rouge-chinese; extra == "all"
-Requires-Dist: ms-opencompass>=0.1.0; extra == "all"
+Requires-Dist: ms-opencompass>=0.1.1; extra == "all"
 Requires-Dist: ms-vlmeval>=0.0.5; extra == "all"
 
 English | [简体中文](README_zh.md)

{evalscope-0.5.4 → evalscope-0.5.5rc1}/evalscope/backend/opencompass/tasks/eval_datasets.py

@@ -7,7 +7,7 @@ with read_base():
     from opencompass.configs.datasets.agieval.agieval_gen_64afd3 import agieval_datasets
     from opencompass.configs.datasets.GaokaoBench.GaokaoBench_gen_5cfe9e import GaokaoBench_datasets
     from opencompass.configs.datasets.humaneval.humaneval_gen_8e312c import humaneval_datasets
-    from opencompass.configs.datasets.mbpp.deprecated_mbpp_gen_1e1056 import mbpp_datasets
+    from opencompass.configs.datasets.mbpp.mbpp_gen_830460 import mbpp_datasets
     from opencompass.configs.datasets.CLUE_C3.CLUE_C3_gen_8c358f import C3_datasets
     from opencompass.configs.datasets.CLUE_CMRC.CLUE_CMRC_gen_1bd3c8 import CMRC_datasets
     from opencompass.configs.datasets.CLUE_DRCD.CLUE_DRCD_gen_1bd3c8 import DRCD_datasets
@@ -45,7 +45,7 @@ with read_base():
     from opencompass.configs.datasets.piqa.piqa_gen_1194eb import piqa_datasets
     from opencompass.configs.datasets.siqa.siqa_gen_e78df3 import siqa_datasets
     from opencompass.configs.datasets.strategyqa.strategyqa_gen_1180a7 import strategyqa_datasets
-    from opencompass.configs.datasets.winogrande.deprecated_winogrande_gen_a9ede5 import winogrande_datasets
+    from opencompass.configs.datasets.winogrande.winogrande_gen_458220 import winogrande_datasets
     from opencompass.configs.datasets.obqa.obqa_gen_9069e4 import obqa_datasets
     from opencompass.configs.datasets.nq.nq_gen_c788f6 import nq_datasets
     from opencompass.configs.datasets.triviaqa.triviaqa_gen_2121ce import triviaqa_datasets

{evalscope-0.5.4 → evalscope-0.5.5rc1}/evalscope/metrics/bundled_rouge_score/rouge_scorer.py

@@ -31,6 +31,7 @@ In these examples settings.xml lists input files and formats.
 from __future__ import absolute_import, division, print_function
 import collections
 import re
+import os
 
 import nltk
 import numpy as np
@@ -38,6 +39,24 @@ import six
 from absl import logging
 from rouge_score import scoring, tokenizers
 from six.moves import map, range
+from evalscope.utils import get_logger
+
+logger = get_logger()
+
+# Deal with nltk punkt_tab.zip tokenizer file to avoid downloading issue
+try:
+    nltk_dir = os.path.join(os.path.expanduser('~'), 'nltk_data/tokenizers')
+    os.makedirs(nltk_dir, exist_ok=True)
+    punkt_path = os.path.join(nltk_dir, 'punkt_tab.zip')
+    punkt_tab_url = 'https://modelscope-open.oss-cn-hangzhou.aliyuncs.com/open_data/nltk_data/punkt_tab.zip'
+
+    if not os.path.exists(punkt_path):
+        os.system(f'wget -P {nltk_dir} {punkt_tab_url}')
+        os.system(f'unzip {punkt_path} -d {nltk_dir}')
+    else:
+        logger.info(f'{punkt_path} already exists, skipping download')
+except Exception as e:
+    logger.error(f'Try to download punkt_tab.zip for nltk failed: {e}')
 
 
 class RougeScorer(scoring.BaseScorer):

evalscope-0.5.5rc1/evalscope/version.py

@@ -0,0 +1,4 @@
+# Copyright (c) Alibaba, Inc. and its affiliates.
+
+__version__ = '0.5.5rc1'
+__release_datetime__ = '2024-09-29 08:00:00'

{evalscope-0.5.4 → evalscope-0.5.5rc1}/evalscope.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: evalscope
-Version: 0.5.4
+Version: 0.5.5rc1
 Summary: EvalScope: Lightweight LLMs Evaluation Framework
 Home-page: https://github.com/modelscope/evalscope
 Author: ModelScope team
@@ -48,7 +48,7 @@ Requires-Dist: transformers_stream_generator
 Requires-Dist: jieba
 Requires-Dist: rouge-chinese
 Provides-Extra: opencompass
-Requires-Dist: ms-opencompass>=0.1.0; extra == "opencompass"
+Requires-Dist: ms-opencompass>=0.1.1; extra == "opencompass"
 Provides-Extra: vlmeval
 Requires-Dist: ms-vlmeval>=0.0.5; extra == "vlmeval"
 Provides-Extra: inner
@@ -111,7 +111,7 @@ Requires-Dist: transformers>=4.33; extra == "all"
 Requires-Dist: transformers_stream_generator; extra == "all"
 Requires-Dist: jieba; extra == "all"
 Requires-Dist: rouge-chinese; extra == "all"
-Requires-Dist: ms-opencompass>=0.1.0; extra == "all"
+Requires-Dist: ms-opencompass>=0.1.1; extra == "all"
 Requires-Dist: ms-vlmeval>=0.0.5; extra == "all"
 
 English | [简体中文](README_zh.md)

{evalscope-0.5.4 → evalscope-0.5.5rc1}/evalscope.egg-info/requires.txt

@@ -64,7 +64,7 @@ transformers>=4.33
 transformers_stream_generator
 jieba
 rouge-chinese
-ms-opencompass>=0.1.0
+ms-opencompass>=0.1.1
 ms-vlmeval>=0.0.5
 
 [inner]
@@ -95,7 +95,7 @@ transformers<4.43,>=4.33
 transformers_stream_generator
 
 [opencompass]
-ms-opencompass>=0.1.0
+ms-opencompass>=0.1.1
 
 [vlmeval]
 ms-vlmeval>=0.0.5

evalscope-0.5.4/evalscope/version.py

@@ -1,4 +0,0 @@
-# Copyright (c) Alibaba, Inc. and its affiliates.
-
-__version__ = '0.5.4'
-__release_datetime__ = '2024-09-19 08:00:00'