jiangzhs/OpenCompass
1
0
Fork 0
mirror of https://github.com/open-compass/opencompass.git synced 2025-05-30 16:03:24 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Update] Update Skywork/Qwen-QwQ (#1728)

Browse Source 
* Update JuderBench

* Support O1-style Prompts

* Update Code

* Update OpenAI

* Update BigCodeBench

* Update BigCodeBench

* Update BigCodeBench

* Update BigCodeBench

* Update BigCodeBench

* Update
This commit is contained in:
Songyang Zhang 2024-12-05 19:30:43 +08:00 committed by GitHub
parent 6181ac1122
commit fb43dd1906
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
49 changed files with 2104 additions and 131 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
configs/datasets/LCBench/lcbench_repeat10_gen.py
View File

@ -1,4 +1,4 @@
from mmengine.config import read_base
with read_base():
from .lcbench_repeat10_gen_5ff288 import LCBench_datasets_repeat10 # noqa: F401, F403
from .lcbench_repeat10_gen_5ff288 import LCBench_repeat10_datasets # noqa: F401, F403

2
configs/datasets/LCBench/lcbench_repeat10_gen_5ff288.py
View File

@ -86,7 +86,7 @@ LC_cn_infer_cfg = dict(
LC_eval_cfg = dict(evaluator=dict(type=LCPassKEvaluator), pred_role='BOT')
LCBench_datasets_repeat10 = [
LCBench_repeat10_datasets = [
dict(
type=LCDataset,
abbr='lcbench_en_repeat10',

2
opencompass/configs/datasets/LCBench/lcbench_repeat10_gen.py
View File

@ -1,4 +1,4 @@
from mmengine.config import read_base
with read_base():
from .lcbench_repeat10_gen_5ff288 import LCBench_datasets_repeat10 # noqa: F401, F403
from .lcbench_repeat10_gen_5ff288 import LCBench_repeat10_datasets # noqa: F401, F403

2
opencompass/configs/datasets/LCBench/lcbench_repeat10_gen_5ff288.py
View File

@ -86,7 +86,7 @@ LC_cn_infer_cfg = dict(
LC_eval_cfg = dict(evaluator=dict(type=LCPassKEvaluator), pred_role='BOT')
LCBench_datasets_repeat10 = [
LCBench_repeat10_datasets = [
dict(
type=LCDataset,
abbr='lcbench_en_repeat10',

87
opencompass/configs/datasets/aime2024/aime2024_0shot_nocot_llmjudge_gen_2b9dc2.py Normal file
View File

@ -0,0 +1,87 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import Aime2024Dataset, MATHEvaluator, math_postprocess_v2
from opencompass.openicl.icl_evaluator import LMEvaluator
from opencompass.datasets import generic_llmjudge_postprocess
aime2024_reader_cfg = dict(
input_columns=['question'],
output_column='answer'
)
aime2024_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN', prompt='{question}\nRemember to put your final answer within \\boxed{}.'),
],
)
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer, max_out_len=2048)
)
GRADER_TEMPLATE = """
Please as a grading expert, judge whether the final answers given by the candidates below are consistent with the standard answers, that is, whether the candidates answered correctly.
Here are some evaluation criteria:
1. Please refer to the given standard answer. You don't need to re-generate the answer to the question because the standard answer has been given. You only need to judge whether the candidate's answer is consistent with the standard answer according to the form of the question. Don't try to answer the original question. You can assume that the standard answer is definitely correct.
2. Because the candidate's answer may be different from the standard answer in the form of expression, before making a judgment, please understand the question and the standard answer first, and then judge whether the candidate's answer is correct, but be careful not to try to answer the original question.
3. Some answers may contain multiple items, such as multiple-choice questions, multiple-select questions, fill-in-the-blank questions, etc. As long as the answer is the same as the standard answer, it is enough. For multiple-select questions and multiple-blank fill-in-the-blank questions, the candidate needs to answer all the corresponding options or blanks correctly to be considered correct.
4. Some answers may be expressed in different ways, such as some answers may be a mathematical expression, some answers may be a textual description, as long as the meaning expressed is the same. And some formulas are expressed in different ways, but they are equivalent and correct.
5. If the prediction is given with \\boxed{}, please ignore the \\boxed{} and only judge whether the candidate's answer is consistent with the standard answer.
Please judge whether the following answers are consistent with the standard answer based on the above criteria. Grade the predicted answer of this new question as one of:
A: CORRECT
B: INCORRECT
Just return the letters "A" or "B", with no text around it.
Here is your task. Simply reply with either CORRECT, INCORRECT. Don't apologize or correct yourself if there was a mistake; we are just trying to grade the answer.
<Original Question Begin>: \n{question}\n<Original Question End>\n\n
<Gold Target Begin>: \n{answer}\n<Gold Target End>\n\n
<Predicted Answer Begin>: \n{prediction}\n<Predicted End>\n\n
Judging the correctness of candidates' answers:
""".strip()
aime2024_eval_cfg = dict(
evaluator=dict(
type=LMEvaluator,
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='SYSTEM',
fallback_role='HUMAN',
prompt="You are a helpful assistant who evaluates the correctness and quality of models' outputs.")
],
round=[
dict(
role='HUMAN',
prompt = GRADER_TEMPLATE
),
]),
),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
pred_role='BOT',
)
aime2024_datasets = [
dict(
abbr='aime2024',
type=Aime2024Dataset,
path='opencompass/aime2024',
reader_cfg=aime2024_reader_cfg,
infer_cfg=aime2024_infer_cfg,
eval_cfg=aime2024_eval_cfg,
mode='singlescore',
)
]

4
opencompass/configs/datasets/bigcodebench/bigcodebench_full_complete_gen.py Normal file
View File

@ -0,0 +1,4 @@
from mmengine.config import read_base
with read_base():
from .bigcodebench_full_complete_gen_faf748 import bigcodebench_full_complete_datasets # noqa: F401, F403

53
opencompass/configs/datasets/bigcodebench/bigcodebench_full_complete_gen_faf748.py Normal file
View File

@ -0,0 +1,53 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import (
BigCodeBenchDataset,
BigCodeBenchEvaluator
)
bigcodebench_full_reader_cfg = dict(
input_columns=['complete_prompt'],
output_column='test',
)
bigcodebench_full_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[dict(role='system',
fallback_role='HUMAN',
prompt='')],
round=[
dict(role='HUMAN', prompt='{complete_prompt}'),
]
)
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer, max_out_len=1024)
)
bigcodebench_full_eval_cfg = dict(
evaluator=dict(
type=BigCodeBenchEvaluator,
release_version='v0.1.2',
eval_type='complete',
remote_execute_api="https://bigcode-bigcodebench-evaluator.hf.space/",
dataset_version='full',
),
pred_role='BOT',
)
bigcodebench_full_complete_datasets = [
dict(
abbr='bigcodebench_full_complete',
type=BigCodeBenchDataset,
path="opencompass/bigcodebench",
reader_cfg=bigcodebench_full_reader_cfg,
infer_cfg=bigcodebench_full_infer_cfg,
eval_cfg=bigcodebench_full_eval_cfg,
release_version='v0.1.2'
)
]

4
opencompass/configs/datasets/bigcodebench/bigcodebench_full_instruct_gen.py Normal file
View File

@ -0,0 +1,4 @@
from mmengine.config import read_base
with read_base():
from .bigcodebench_full_instruct_gen_8815eb import bigcodebench_full_instruct_datasets # noqa: F401, F403

53
opencompass/configs/datasets/bigcodebench/bigcodebench_full_instruct_gen_8815eb.py Normal file
View File

@ -0,0 +1,53 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import (
BigCodeBenchDataset,
BigCodeBenchEvaluator
)
bigcodebench_full_reader_cfg = dict(
input_columns=['instruct_prompt'],
output_column='test',
)
bigcodebench_full_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[dict(role='system',
fallback_role='HUMAN',
prompt='')],
round=[
dict(role='HUMAN', prompt='{instruct_prompt}'),
]
)
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer, max_out_len=8192)
)
bigcodebench_full_eval_cfg = dict(
evaluator=dict(
type=BigCodeBenchEvaluator,
release_version='v0.1.2',
eval_type='instruct',
remote_execute_api="https://bigcode-bigcodebench-evaluator.hf.space/",
dataset_version='full',
),
pred_role='BOT',
)
bigcodebench_full_instruct_datasets = [
dict(
abbr='bigcodebench_full_instruct',
type=BigCodeBenchDataset,
path="opencompass/bigcodebench",
reader_cfg=bigcodebench_full_reader_cfg,
infer_cfg=bigcodebench_full_infer_cfg,
eval_cfg=bigcodebench_full_eval_cfg,
release_version='v0.1.2'
)
]

4
opencompass/configs/datasets/bigcodebench/bigcodebench_hard_complete_gen.py Normal file
View File

@ -0,0 +1,4 @@
from mmengine.config import read_base
with read_base():
from .bigcodebench_hard_complete_gen_faf748 import bigcodebench_hard_complete_datasets # noqa: F401, F403

54
opencompass/configs/datasets/bigcodebench/bigcodebench_hard_complete_gen_faf748.py Normal file
View File

@ -0,0 +1,54 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import (
BigCodeBenchDataset,
BigCodeBenchEvaluator
)
bigcodebench_hard_reader_cfg = dict(
input_columns=['complete_prompt'],
output_column='test',
)
bigcodebench_hard_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[dict(role='system',
fallback_role='HUMAN',
prompt='')],
round=[
dict(role='HUMAN', prompt='{complete_prompt}'),
]
)
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer, max_out_len=1024)
)
bigcodebench_hard_eval_cfg = dict(
evaluator=dict(
type=BigCodeBenchEvaluator,
release_version='v0.1.2',
eval_type='complete',
remote_execute_api="https://bigcode-bigcodebench-evaluator.hf.space/",
dataset_version='hard',
),
pred_role='BOT',
)
bigcodebench_hard_complete_datasets = [
dict(
abbr='bigcodebench_hard_complete',
type=BigCodeBenchDataset,
path="opencompass/bigcodebench",
reader_cfg=bigcodebench_hard_reader_cfg,
infer_cfg=bigcodebench_hard_infer_cfg,
eval_cfg=bigcodebench_hard_eval_cfg,
release_version='v0.1.2',
dataset_version='hard',
)
]

4
opencompass/configs/datasets/bigcodebench/bigcodebench_hard_instruct_gen.py Normal file
View File

@ -0,0 +1,4 @@
from mmengine.config import read_base
with read_base():
from .bigcodebench_hard_instruct_gen_8815eb import bigcodebench_hard_instruct_datasets # noqa: F401, F403

54
opencompass/configs/datasets/bigcodebench/bigcodebench_hard_instruct_gen_8815eb.py Normal file
View File

@ -0,0 +1,54 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import (
BigCodeBenchDataset,
BigCodeBenchEvaluator
)
bigcodebench_hard_reader_cfg = dict(
input_columns=['instruct_prompt'],
output_column='test',
)
bigcodebench_hard_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[dict(role='system',
fallback_role='HUMAN',
prompt='')],
round=[
dict(role='HUMAN', prompt='{instruct_prompt}'),
]
)
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer, max_out_len=8192)
)
bigcodebench_hard_eval_cfg = dict(
evaluator=dict(
type=BigCodeBenchEvaluator,
release_version='v0.1.2',
eval_type='instruct',
remote_execute_api="https://bigcode-bigcodebench-evaluator.hf.space/",
dataset_version='hard',
),
pred_role='BOT',
)
bigcodebench_hard_instruct_datasets = [
dict(
abbr='bigcodebench_hard_instruct',
type=BigCodeBenchDataset,
path="opencompass/bigcodebench",
reader_cfg=bigcodebench_hard_reader_cfg,
infer_cfg=bigcodebench_hard_infer_cfg,
eval_cfg=bigcodebench_hard_eval_cfg,
release_version='v0.1.2',
dataset_version='hard',
)
]

173
opencompass/configs/datasets/cmmlu/cmmlu_0shot_nocot_llmjudge_gen_e1cd9a.py Normal file
View File

@ -0,0 +1,173 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import AccEvaluator
from opencompass.datasets import CMMLUDataset
from opencompass.utils.text_postprocessors import match_answer_pattern
from opencompass.openicl.icl_evaluator import LMEvaluator
from opencompass.datasets import generic_llmjudge_postprocess
cmmlu_subject_mapping = {
'agronomy': '农学',
'anatomy': '解剖学',
'ancient_chinese': '古汉语',
'arts': '艺术学',
'astronomy': '天文学',
'business_ethics': '商业伦理',
'chinese_civil_service_exam': '中国公务员考试',
'chinese_driving_rule': '中国驾驶规则',
'chinese_food_culture': '中国饮食文化',
'chinese_foreign_policy': '中国外交政策',
'chinese_history': '中国历史',
'chinese_literature': '中国文学',
'chinese_teacher_qualification': '中国教师资格',
'clinical_knowledge': '临床知识',
'college_actuarial_science': '大学精算学',
'college_education': '大学教育学',
'college_engineering_hydrology': '大学工程水文学',
'college_law': '大学法律',
'college_mathematics': '大学数学',
'college_medical_statistics': '大学医学统计',
'college_medicine': '大学医学',
'computer_science': '计算机科学',
'computer_security': '计算机安全',
'conceptual_physics': '概念物理学',
'construction_project_management': '建设工程管理',
'economics': '经济学',
'education': '教育学',
'electrical_engineering': '电气工程',
'elementary_chinese': '小学语文',
'elementary_commonsense': '小学常识',
'elementary_information_and_technology': '小学信息技术',
'elementary_mathematics': '初等数学',
'ethnology': '民族学',
'food_science': '食品科学',
'genetics': '遗传学',
'global_facts': '全球事实',
'high_school_biology': '高中生物',
'high_school_chemistry': '高中化学',
'high_school_geography': '高中地理',
'high_school_mathematics': '高中数学',
'high_school_physics': '高中物理学',
'high_school_politics': '高中政治',
'human_sexuality': '人类性行为',
'international_law': '国际法学',
'journalism': '新闻学',
'jurisprudence': '法理学',
'legal_and_moral_basis': '法律与道德基础',
'logical': '逻辑学',
'machine_learning': '机器学习',
'management': '管理学',
'marketing': '市场营销',
'marxist_theory': '马克思主义理论',
'modern_chinese': '现代汉语',
'nutrition': '营养学',
'philosophy': '哲学',
'professional_accounting': '专业会计',
'professional_law': '专业法学',
'professional_medicine': '专业医学',
'professional_psychology': '专业心理学',
'public_relations': '公共关系',
'security_study': '安全研究',
'sociology': '社会学',
'sports_science': '体育学',
'traditional_chinese_medicine': '中医中药',
'virology': '病毒学',
'world_history': '世界历史',
'world_religions': '世界宗教'
}
QUERY_TEMPLATE = """
你回答的最后一行**必须**是以下格式 '答案: $选项' (不带引号), 其中选项是ABCD之一.
{question}
A) {A}
B) {B}
C) {C}
D) {D}
""".strip()
GRADER_TEMPLATE = """
Please as a grading expert, judge whether the final answers given by the candidates below are consistent with the standard answers, that is, whether the candidates answered correctly.
Here are some evaluation criteria:
1. Please refer to the given standard answer. You don't need to re-generate the answer to the question because the standard answer has been given. You only need to judge whether the candidate's answer is consistent with the standard answer according to the form of the question. Don't try to answer the original question. You can assume that the standard answer is definitely correct.
2. Because the candidate's answer may be different from the standard answer in the form of expression, before making a judgment, please understand the question and the standard answer first, and then judge whether the candidate's answer is correct, but be careful not to try to answer the original question.
3. Some answers may contain multiple items, such as multiple-choice questions, multiple-select questions, fill-in-the-blank questions, etc. As long as the answer is the same as the standard answer, it is enough. For multiple-select questions and multiple-blank fill-in-the-blank questions, the candidate needs to answer all the corresponding options or blanks correctly to be considered correct.
4. Some answers may be expressed in different ways, such as some answers may be a mathematical expression, some answers may be a textual description, as long as the meaning expressed is the same. And some formulas are expressed in different ways, but they are equivalent and correct.
Please judge whether the following answers are consistent with the standard answer based on the above criteria. Grade the predicted answer of this new question as one of:
A: CORRECT
B: INCORRECT
Just return the letters "A" or "B", with no text around it.
Here is your task. Simply reply with either CORRECT, INCORRECT. Don't apologize or correct yourself if there was a mistake; we are just trying to grade the answer.
<Original Question Begin>: \n {question}\n A) {A}\n B) {B}\n C) {C}\n D) {D}\n<Original Question End>\n\n
<Gold Target Begin>: \n{answer}\n<Gold Target End>\n\n
<Predicted Answer Begin>: \n{prediction}\n<Predicted End>\n\n
Judging the correctness of candidates' answers:
""".strip()
cmmlu_all_sets = list(cmmlu_subject_mapping.keys())
cmmlu_datasets = []
for _name in cmmlu_all_sets:
_ch_name = cmmlu_subject_mapping[_name]
prompt_prefix = f'请回答以下关于{_ch_name}的单项选择题, '
cmmlu_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN', prompt=prompt_prefix+QUERY_TEMPLATE),
],
),
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer),
)
cmmlu_eval_cfg = dict(
evaluator=dict(
type=LMEvaluator,
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='SYSTEM',
fallback_role='HUMAN',
prompt="You are a helpful assistant who evaluates the correctness and quality of models' outputs.")
],
round=[
dict(
role='HUMAN',
prompt = GRADER_TEMPLATE
),
]),
),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
pred_role='BOT',
)
cmmlu_datasets.append(
dict(
type=CMMLUDataset,
path='opencompass/cmmlu',
name=_name,
abbr=f'cmmlu-{_name}',
reader_cfg=dict(
input_columns=['question', 'A', 'B', 'C', 'D'],
output_column='answer',
train_split='dev',
test_split='test'),
infer_cfg=cmmlu_infer_cfg,
eval_cfg=cmmlu_eval_cfg,
mode='singlescore',
))
del _name, _ch_name

101
opencompass/configs/datasets/gpqa/gpqa_0shot_nocot_llmjudge_gen_772ea0.py Normal file
View File

@ -0,0 +1,101 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import GPQADataset, GPQA_Simple_Eval_postprocess, GPQAEvaluator
from opencompass.openicl.icl_evaluator import LMEvaluator
from opencompass.datasets import generic_llmjudge_postprocess
# openai_simple_eval prompt
align_prompt = """
Answer the following multiple choice question. The last line of your response should be of the following format: 'ANSWER: $LETTER' (without quotes) where LETTER is one of ABCD.
{question}
A) {A}
B) {B}
C) {C}
D) {D}
""".strip()
GRADER_TEMPLATE = """
Please as a grading expert, judge whether the final answers given by the candidates below are consistent with the standard answers, that is, whether the candidates answered correctly.
Here are some evaluation criteria:
1. Please refer to the given standard answer. You don't need to re-generate the answer to the question because the standard answer has been given. You only need to judge whether the candidate's answer is consistent with the standard answer according to the form of the question. Don't try to answer the original question. You can assume that the standard answer is definitely correct.
2. Because the candidate's answer may be different from the standard answer in the form of expression, before making a judgment, please understand the question and the standard answer first, and then judge whether the candidate's answer is correct, but be careful not to try to answer the original question.
3. Some answers may contain multiple items, such as multiple-choice questions, multiple-select questions, fill-in-the-blank questions, etc. As long as the answer is the same as the standard answer, it is enough. For multiple-select questions and multiple-blank fill-in-the-blank questions, the candidate needs to answer all the corresponding options or blanks correctly to be considered correct.
4. Some answers may be expressed in different ways, such as some answers may be a mathematical expression, some answers may be a textual description, as long as the meaning expressed is the same. And some formulas are expressed in different ways, but they are equivalent and correct.
Please judge whether the following answers are consistent with the standard answer based on the above criteria. Grade the predicted answer of this new question as one of:
A: CORRECT
B: INCORRECT
Just return the letters "A" or "B", with no text around it.
Here is your task. Simply reply with either CORRECT, INCORRECT. Don't apologize or correct yourself if there was a mistake; we are just trying to grade the answer.
<Original Question Begin>: {question}\n A) {A}\n B) {B}\n C) {C}\n D) {D}\n<Original Question End>\n\n
<Gold Target Begin>: \n{answer}\n<Gold Target End>\n\n
<Predicted Answer Begin>: \n{prediction}\n<Predicted End>\n\n
Judging the correctness of candidates' answers:
""".strip()
gpqa_reader_cfg = dict(
input_columns=['question', 'A', 'B', 'C', 'D'],
output_column='answer')
gpqa_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN', prompt=align_prompt),
], )),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer))
gpqa_eval_cfg = dict(
evaluator=dict(
type=LMEvaluator,
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='SYSTEM',
fallback_role='HUMAN',
prompt="You are a helpful assistant who evaluates the correctness and quality of models' outputs.")
],
round=[
dict(
role='HUMAN',
prompt = GRADER_TEMPLATE
),
]),
),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
pred_role='BOT',
)
gpqa_datasets = []
gpqa_subsets = {
# 'extended': 'gpqa_extended.csv',
# 'main': 'gpqa_main.csv',
'diamond': 'gpqa_diamond.csv'
}
for split in list(gpqa_subsets.keys()):
gpqa_datasets.append(
dict(
abbr='GPQA_' + split,
type=GPQADataset,
path='./data/gpqa/',
name=gpqa_subsets[split],
reader_cfg=gpqa_reader_cfg,
infer_cfg=gpqa_infer_cfg,
eval_cfg=gpqa_eval_cfg,
mode='singlescore',
)
)

109
opencompass/configs/datasets/korbench/korbench_single_0shot_llmjudge_gen.py Normal file
View File

@ -0,0 +1,109 @@
from opencompass.datasets.korbench.korbench import korbenchDataset, korbenchEvaluator
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_evaluator import LMEvaluator
from opencompass.datasets import generic_llmjudge_postprocess
categories = ["cipher", "counterfactual", "logic", "operation", "puzzle"]
GRADER_TEMPLATE = """
Please as a grading expert, judge whether the final answers given by the candidates below are consistent with the standard answers, that is, whether the candidates answered correctly.
Here are some evaluation criteria:
1. Please refer to the given standard answer. You don't need to re-generate the answer to the question because the standard answer has been given. You only need to judge whether the candidate's answer is consistent with the standard answer according to the form of the question. Don't try to answer the original question. You can assume that the standard answer is definitely correct.
2. Because the candidate's answer may be different from the standard answer in the form of expression, before making a judgment, please understand the question and the standard answer first, and then judge whether the candidate's answer is correct, but be careful not to try to answer the original question.
3. Some answers may contain multiple items, such as multiple-choice questions, multiple-select questions, fill-in-the-blank questions, etc. As long as the answer is the same as the standard answer, it is enough. For multiple-select questions and multiple-blank fill-in-the-blank questions, the candidate needs to answer all the corresponding options or blanks correctly to be considered correct.
4. Some answers may be expressed in different ways, such as some answers may be a mathematical expression, some answers may be a textual description, as long as the meaning expressed is the same. And some formulas are expressed in different ways, but they are equivalent and correct.
5. If the prediction is given with \\boxed{}, please ignore the \\boxed{} and only judge whether the candidate's answer is consistent with the standard answer.
Please judge whether the following answers are consistent with the standard answer based on the above criteria. Grade the predicted answer of this new question as one of:
A: CORRECT
B: INCORRECT
Just return the letters "A" or "B", with no text around it.
Here is your task. Simply reply with either CORRECT, INCORRECT. Don't apologize or correct yourself if there was a mistake; we are just trying to grade the answer.
<Original Question Begin>: \n{prompt}\n<Original Question End>\n\n
<Gold Target Begin>: \n{answer}\n<Gold Target End>\n\n
<Predicted Answer Begin>: \n{prediction}\n<Predicted End>\n\n
Judging the correctness of candidates' answers:
""".strip()
korbench_0shot_single_datasets = []
for category in categories:
# Prompt template
prompt_template = dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role="HUMAN",
prompt=""
)
],
round=[
dict(
role="HUMAN",
prompt="{prompt}" # f-string
)
]
)
)
# Reader configuration
reader_cfg = dict(
input_columns=["prompt"],
output_column="answer",
)
# Inference configuration
infer_cfg = dict(
prompt_template=prompt_template,
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer, max_out_len=1024),
)
# Evaluation configuration
eval_cfg = dict(
evaluator=dict(
type=LMEvaluator,
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='SYSTEM',
fallback_role='HUMAN',
prompt="You are a helpful assistant who evaluates the correctness and quality of models' outputs.")
],
round=[
dict(
role='HUMAN',
prompt = GRADER_TEMPLATE
),
]),
),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
pred_role='BOT',
)
# Dataset
korbench_dataset = dict(
type=korbenchDataset,
abbr=f"korbench_{category}",
path="opencompass/korbench",
prompt_mode='0_shot',
category=category,
reader_cfg=reader_cfg,
infer_cfg=infer_cfg,
eval_cfg=eval_cfg,
mode='singlescore',
)
korbench_0shot_single_datasets.append(korbench_dataset)

4
opencompass/configs/datasets/livereasonbench/livereasonbench_gen.py Normal file
View File

@ -0,0 +1,4 @@
from mmengine.config import read_base
with read_base():
from .livereasonbench_gen_0283c3 import simpleqa_datasets # noqa: F401, F403

136
opencompass/configs/datasets/livereasonbench/livereasonbench_gen_f990de.py Normal file
View File

@ -0,0 +1,136 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import LMEvaluator
# from opencompass.datasets import SimpleQADataset, simpleqa_postprocess
from opencompass.datasets import LiveReasonBenchDataset, livereasonbench_postprocess
GRADER_TEMPLATE = """
Your job is to look at a question, a gold target, and a predicted answer, and then assign a grade of either ["CORRECT", "INCORRECT", "NOT_ATTEMPTED"].
First, I will give examples of each grade, and then you will grade a new example.
The following are examples of CORRECT predicted answers.
```
Question: What are the names of Barack Obama's children?
Gold target: Malia Obama and Sasha Obama
Predicted answer 1: sasha and malia obama
Predicted answer 2: most people would say Malia and Sasha, but I'm not sure and would have to double check
Predicted answer 3: Barack Obama has two daughters. Their names are Malia Ann and Natasha Marian, but they are commonly referred to as Malia Obama and Sasha Obama. Malia was born on July 4, 1998, and Sasha was born on June 10, 2001.
```
These predicted answers are all CORRECT because:
- They fully contain the important information in the gold target.
- They do not contain any information that contradicts the gold target.
- Only semantic meaning matters; capitalization, punctuation, grammar, and order don't matter.
- Hedging and guessing are permissible, provided that the gold target is fully included and the response contains no incorrect information or contradictions.
The following are examples of INCORRECT predicted answers.
```
Question: What are the names of Barack Obama's children?
Gold target: Malia and Sasha
Predicted answer 1: Malia.
Predicted answer 2: Malia, Sasha, and Susan.
Predicted answer 3: Barack Obama does not have any children.
Predicted answer 4: I think it's either Malia and Sasha. Or it could be Malia and Jackie. Or it could be Joey and Malia.
Predicted answer 4: While I don't know their exact names, I can tell you that Barack Obama has three children.
Predicted answer 5: It's possible you may mean Betsy and Olivia. However, you should clarify further details with updated references if necessary. Is that the correct answer?
Predicted answer 6: It may be the case that Obama's child is named James. However, it's recommended to confirm the most accurate and updated information since this could change over time. This model may not always reflect the most current information.
```
These predicted answers are all INCORRECT because:
- A factual statement in the answer contradicts the gold target. Incorrect statements that have some hedging (e.g., "it is possible that", "although i'm not sure, i think") are also considered incorrect.
The following are examples of NOT_ATTEMPTED predicted answers.
```
Question: What are the names of Barack Obama's children?
Gold target: Malia and Sasha
Predicted answer 1: I don't know.
Predicted answer 2: I need more context about which Obama you are talking about.
Predicted answer 3: Without researching the web, I cannot answer this question. However, I can tell you that Barack Obama has two children.
Predicted answer 4: Barack Obama has two children. I know that one of them is Malia, but I'm not sure about the other one.
```
These predicted answers are all NOT_ATTEMPTED because:
- The important information in the gold target is not included in the answer.
- No statements in the answer contradict the gold target.
Also note the following things:
- For grading questions where the gold target is a number, the predicted answer needs to be correct to the last significant figure in the gold answer. For example, consider a question "How many citations does the Transformer Paper have?" with gold target "120k".
- Predicted answers "120k", "124k", and 115k" are all CORRECT.
- Predicted answers "100k" and "113k" are INCORRECT.
- Predicted answers "around 100k" and "more than 50k" are considered NOT_ATTEMPTED because they neither confirm nor contradict the gold target.
- The gold target may contain more information than the question. In such cases, the predicted answer only needs to contain the information that is in the question.
- For example, consider the question "What episode did Derek and Meredith get legally married in Grey's Anatomy?" with gold target "Season 7, Episode 20: White Wedding". Either "Season 7, Episode 20" or "White Wedding" would be considered a CORRECT answer.
- Do not punish predicted answers if they omit information that would be clearly inferred from the question.
- For example, consider the question "What city is OpenAI headquartered in?" and the gold target "San Francisco, California". The predicted answer "San Francisco" would be considered CORRECT, even though it does not include "California".
- Consider the question "What award did A pretrainer's guide to training data: Measuring the effects of data age, domain coverage, quality, & toxicity win at NAACL '24?", the gold target is "Outstanding Paper Award". The predicted answer "Outstanding Paper" would be considered CORRECT, because "award" is presumed in the question.
- For the question "What is the height of Jason Wei in meters?", the gold target is "1.73 m". The predicted answer "1.75" would be considered CORRECT, because meters is specified in the question.
- For the question "What is the name of Barack Obama's wife?", the gold target is "Michelle Obama". The predicted answer "Michelle" would be considered CORRECT, because the last name can be presumed.
- Do not punish for typos in people's name if it's clearly the same name.
- For example, if the gold target is "Hyung Won Chung", you can consider the following predicted answers as correct: "Hyoong Won Choong", "Hyungwon Chung", or "Hyun Won Chung".
Grade the predicted answer of this new question as one of:
A: CORRECT
B: INCORRECT
C: NOT_ATTEMPTED
Just return the letters "A", "B", or "C", with no text around it.
Here is a new example. Simply reply with either CORRECT, INCORRECT, NOT ATTEMPTED. Don't apologize or correct yourself if there was a mistake; we are just trying to grade the answer.
```
Question: {question}
Gold target: {answer}
Predicted answer: {prediction}
```
""".strip()
livereasonbench_reader_cfg = dict(input_columns=['question'], output_column='answer')
livereasonbench_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN', prompt="Question: {question}\n"),
],
)),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer, max_out_len=16384))
livereasonbench_eval_cfg = dict(
evaluator=dict(
type=LMEvaluator,
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='SYSTEM',
fallback_role='HUMAN',
prompt="You are a helpful assistant who evaluates the correctness and quality of models' outputs.")
],
round=[
dict(
role='HUMAN',
prompt = GRADER_TEMPLATE
),
]),
),
dict_postprocessor=dict(type=livereasonbench_postprocess),
),
pred_role='BOT',
)
livereasonbench_datasets = [
dict(
abbr='LiveReasonBench-20241202',
type=LiveReasonBenchDataset,
path='opencompass/LiveReasonBench',
reader_cfg=livereasonbench_reader_cfg,
infer_cfg=livereasonbench_infer_cfg,
eval_cfg=livereasonbench_eval_cfg,
version='livereasonbench-20241202',
mode='singlescore',
)
]

94
opencompass/configs/datasets/math/math_prm800k_500_0shot_nocot_llmjudge_gen_63a000.py
View File

@ -1,40 +1,11 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import MATHDataset, MATHEvaluator, math_postprocess_v2, normalize_final_answer
from opencompass.datasets import MATHDataset, MATHEvaluator, math_postprocess_v2, GaoKaoMATHEvaluator
# from opencompass.utils.model_postprocessors import naive_model_postprocess, xfinder_postprocess
from opencompass.utils.postprocessors.naive import MATH_NAVIE_PROMPT_TEMPLATE
# ----------------------------- Eval Parameters -----------------------------
## Postprocess function
post_func = 're' # 're', 'xfinder_model', 'naive_model'
## Evalute function
eval_func = 'naive_model' # 're', 'naive_model'
from opencompass.openicl.icl_evaluator import LMEvaluator
from opencompass.datasets import generic_llmjudge_postprocess
from opencompass.datasets import MATHDataset
## Model api url
# xfinder_url = 'http://0.0.0.0:23333/v1' # for 'xFinder-qwen1505' if post_func is 'xfinder_model'
# naive_model_name = 'Qwen/Qwen2.5-72B-Instruct' # replace with your model name
naive_model_name = 'dlc_model'
# naive_model_url = [
# 'http://172.30.56.38:23001/v1',
# ] # Multi-apis for accerlation
naive_model_url = [
"http://172.30.56.38:23001/v1",
"http://172.30.8.4:23003/v1",
"http://172.30.8.14:23002/v1",
"http://172.30.48.80:23004/v1",
"http://172.30.56.132:23005/v1",
"http://172.30.16.115:23006/v1",
"http://172.30.48.82:23007/v1",
"http://172.30.24.53:23008/v1",
"http://172.30.56.141:23009/v1",
"http://172.30.8.35:23010/v1",
"http://172.30.48.85:23011/v1",
"http://172.30.16.116:23012/v1"
]
# ----------------------------- Detailed Config -----------------------------
math_reader_cfg = dict(input_columns=['problem'], output_column='solution')
@ -53,25 +24,57 @@ math_infer_cfg = dict(
)
if post_func == 're':
pred_postprocessor = dict(type=math_postprocess_v2)
GRADER_TEMPLATE = """
Please as a grading expert, judge whether the final answers given by the candidates below are consistent with the standard answers, that is, whether the candidates answered correctly.
Here are some evaluation criteria:
1. Please refer to the given standard answer. You don't need to re-generate the answer to the question because the standard answer has been given. You only need to judge whether the candidate's answer is consistent with the standard answer according to the form of the question. Don't try to answer the original question. You can assume that the standard answer is definitely correct.
2. Because the candidate's answer may be different from the standard answer in the form of expression, before making a judgment, please understand the question and the standard answer first, and then judge whether the candidate's answer is correct, but be careful not to try to answer the original question.
3. Some answers may contain multiple items, such as multiple-choice questions, multiple-select questions, fill-in-the-blank questions, etc. As long as the answer is the same as the standard answer, it is enough. For multiple-select questions and multiple-blank fill-in-the-blank questions, the candidate needs to answer all the corresponding options or blanks correctly to be considered correct.
4. Some answers may be expressed in different ways, such as some answers may be a mathematical expression, some answers may be a textual description, as long as the meaning expressed is the same. And some formulas are expressed in different ways, but they are equivalent and correct.
5. If the prediction is given with \\boxed{}, please ignore the \\boxed{} and only judge whether the candidate's answer is consistent with the standard answer.
Please judge whether the following answers are consistent with the standard answer based on the above criteria. Grade the predicted answer of this new question as one of:
A: CORRECT
B: INCORRECT
Just return the letters "A" or "B", with no text around it.
Here is your task. Simply reply with either CORRECT, INCORRECT. Don't apologize or correct yourself if there was a mistake; we are just trying to grade the answer.
if eval_func == 're':
evaluator = dict(type=MATHEvaluator, version='v2')
elif eval_func == 'naive_model':
evaluator = dict(
type=GaoKaoMATHEvaluator,
judge_model_name=naive_model_name,
url=naive_model_url,
)
<Original Question Begin>: \n{problem}\n<Original Question End>\n\n
<Gold Target Begin>: \n{solution}\n<Gold Target End>\n\n
<Predicted Answer Begin>: \n{prediction}\n<Predicted End>\n\n
Judging the correctness of candidates' answers:
""".strip()
# postprocess v2
# Evaluation configuration
math_eval_cfg = dict(
evaluator=evaluator,
pred_postprocessor=pred_postprocessor,
evaluator=dict(
type=LMEvaluator,
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='SYSTEM',
fallback_role='HUMAN',
prompt="You are a helpful assistant who evaluates the correctness and quality of models' outputs.")
],
round=[
dict(
role='HUMAN',
prompt = GRADER_TEMPLATE
),
]),
),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
pred_role='BOT',
)
math_datasets = [
dict(
type=MATHDataset,
@ -81,5 +84,6 @@ math_datasets = [
reader_cfg=math_reader_cfg,
infer_cfg=math_infer_cfg,
eval_cfg=math_eval_cfg,
mode='singlescore',
)
]

104
opencompass/configs/datasets/mmlu/mmlu_openai_0shot_nocot_llmjudge_gen_216503.py Normal file
View File

@ -0,0 +1,104 @@
from mmengine.config import read_base
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import AccEvaluator
from opencompass.datasets import MMLUDataset
from opencompass.utils.text_postprocessors import match_answer_pattern
from opencompass.openicl.icl_evaluator import LMEvaluator
from opencompass.datasets import generic_llmjudge_postprocess
with read_base():
# from .....configs.datasets.mmlu.mmlu_all_sets import mmlu_all_sets
from .mmlu_stem_sets import mmlu_all_sets
# None of the mmlu dataset in huggingface is correctly parsed, so we use our own dataset reader
# Please download the dataset from https://people.eecs.berkeley.edu/~hendrycks/data.tar
QUERY_TEMPLATE = """
Answer the following multiple choice question. The last line of your response should be of the following format: 'ANSWER: $LETTER' (without quotes) where LETTER is one of ABCD.
{input}
A) {A}
B) {B}
C) {C}
D) {D}
""".strip()
GRADER_TEMPLATE = """
Please as a grading expert, judge whether the final answers given by the candidates below are consistent with the standard answers, that is, whether the candidates answered correctly.
Here are some evaluation criteria:
1. Please refer to the given standard answer. You don't need to re-generate the answer to the question because the standard answer has been given. You only need to judge whether the candidate's answer is consistent with the standard answer according to the form of the question. Don't try to answer the original question. You can assume that the standard answer is definitely correct.
2. Because the candidate's answer may be different from the standard answer in the form of expression, before making a judgment, please understand the question and the standard answer first, and then judge whether the candidate's answer is correct, but be careful not to try to answer the original question.
3. Some answers may contain multiple items, such as multiple-choice questions, multiple-select questions, fill-in-the-blank questions, etc. As long as the answer is the same as the standard answer, it is enough. For multiple-select questions and multiple-blank fill-in-the-blank questions, the candidate needs to answer all the corresponding options or blanks correctly to be considered correct.
4. Some answers may be expressed in different ways, such as some answers may be a mathematical expression, some answers may be a textual description, as long as the meaning expressed is the same. And some formulas are expressed in different ways, but they are equivalent and correct.
Please judge whether the following answers are consistent with the standard answer based on the above criteria. Grade the predicted answer of this new question as one of:
A: CORRECT
B: INCORRECT
Just return the letters "A" or "B", with no text around it.
Here is your task. Simply reply with either CORRECT, INCORRECT. Don't apologize or correct yourself if there was a mistake; we are just trying to grade the answer.
<Original Question Begin>: {input}\n A) {A}\n B) {B}\n C) {C}\n D) {D}\n<Original Question End>\n\n
<Gold Target Begin>: \n{target}\n<Gold Target End>\n\n
<Predicted Answer Begin>: \n{prediction}\n<Predicted End>\n\n
Judging the correctness of candidates' answers:
""".strip()
mmlu_reader_cfg = dict(
input_columns=['input', 'A', 'B', 'C', 'D'],
output_column='target',
train_split='dev')
mmlu_datasets = []
for name in mmlu_all_sets:
mmlu_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN', prompt=QUERY_TEMPLATE),
],
),
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer),
)
mmlu_eval_cfg = dict(
evaluator=dict(
type=LMEvaluator,
prompt_template=dict(
type=PromptTemplate,
template=dict(
begin=[
dict(
role='SYSTEM',
fallback_role='HUMAN',
prompt="You are a helpful assistant who evaluates the correctness and quality of models' outputs.")
],
round=[
dict(
role='HUMAN',
prompt = GRADER_TEMPLATE
),
]),
),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
pred_role='BOT',
)
mmlu_datasets.append(
dict(
abbr=f'lukaemon_mmlu_{name}',
type=MMLUDataset,
path='opencompass/mmlu',
name=name,
reader_cfg=mmlu_reader_cfg,
infer_cfg=mmlu_infer_cfg,
eval_cfg=mmlu_eval_cfg,
mode='singlescore',
))

3
opencompass/configs/datasets/mmlu/mmlu_stem_sets.py Normal file
View File

@ -0,0 +1,3 @@
mmlu_all_sets = [
'abstract_algebra', 'anatomy', 'astronomy', 'college_biology', 'college_chemistry', 'college_computer_science', 'college_mathematics', 'college_physics', 'computer_security', 'conceptual_physics', 'electrical_engineering', 'elementary_mathematics', 'high_school_biology', 'high_school_chemistry', 'high_school_computer_science', 'high_school_mathematics', 'high_school_physics', 'high_school_statistics', 'machine_learning'
]

15
opencompass/configs/models/qwq/lmdeploy_qwq_32b_preview.py Normal file
View File

@ -0,0 +1,15 @@
from opencompass.models import TurboMindModelwithChatTemplate
models = [
dict(
type=TurboMindModelwithChatTemplate,
abbr='QwQ-32B-Preview',
path='Qwen/QwQ-32B-Preview',
engine_config=dict(session_len=32768, max_batch_size=16, tp=2),
gen_config=dict(top_k=1, temperature=1e-6, top_p=0.9, max_new_tokens=8192),
max_seq_len=32768,
max_out_len=8192,
batch_size=16,
run_cfg=dict(num_gpus=2),
)
]

16
opencompass/configs/models/skywork/lmdeploy_skywork_o1_open_llama3_1_8b_instruct.py Normal file
View File

@ -0,0 +1,16 @@
from opencompass.models import TurboMindModelwithChatTemplate
models = [
dict(
type=TurboMindModelwithChatTemplate,
abbr='Skywork-o1-Open-Llama-3_1-8B-turbomind',
path='Skywork/Skywork-o1-Open-Llama-3.1-8B',
engine_config=dict(max_batch_size=16, tp=1),
gen_config=dict(top_k=1, temperature=1e-6, top_p=0.9, max_new_tokens=4096),
max_seq_len=16384,
max_out_len=8192,
batch_size=16,
run_cfg=dict(num_gpus=1),
stop_words=['<|end_of_text|>', '<|eot_id|>'],
)
]

4
opencompass/datasets/__init__.py
View File

@ -10,6 +10,7 @@ from .arc_prize_public_evaluation import * # noqa: F401, F403
from .ax import * # noqa: F401, F403
from .babilong import * # noqa: F401, F403
from .bbh import * # noqa: F401, F403
from .bigcodebench import * # noqa: F401, F403
from .boolq import * # noqa: F401, F403
from .bustum import * # noqa: F401, F403
from .c3 import * # noqa: F401, F403
@ -49,6 +50,7 @@ from .flores import * # noqa: F401, F403
from .game24 import * # noqa: F401, F403
from .gaokao_math import * # noqa: F401, F403
from .GaokaoBench import * # noqa: F401, F403
from .generic import * # noqa: F401, F403
from .govrepcrs import * # noqa: F401, F403
from .gpqa import * # noqa: F401, F403
from .gsm8k import * # noqa: F401, F403
@ -73,6 +75,8 @@ from .LCBench import * # noqa: F401, F403
from .lcsts import * # noqa: F401, F403
from .leval import * # noqa: F401, F403
from .livecodebench import * # noqa: F401, F403
from .livemathbench import * # noqa: F401, F403
from .livereasonbench import * # noqa: F401, F403
from .llm_compression import LLMCompressionDataset # noqa: F401, F403
from .longbench import * # noqa: F401, F403
from .lveval import * # noqa: F401, F403

2
opencompass/datasets/aime2024.py
View File

@ -12,7 +12,7 @@ from .base import BaseDataset
class Aime2024Dataset(BaseDataset):
@staticmethod
def load(path):
def load(path, **kwargs):
path = get_data_path(path)
dataset = []
with open(path, 'r') as f:

1
opencompass/datasets/bigcodebench/__init__.py Normal file
View File

@ -0,0 +1 @@
from .bigcodebench import BigCodeBenchDataset, BigCodeBenchEvaluator # noqa

169
opencompass/datasets/bigcodebench/bigcodebench.py Normal file
View File

@ -0,0 +1,169 @@
# Copyright (c) 2024, BigCodeBench and its contributors.
# Copyright (c) 2023, OpenCompass and its contributors.
import os
import time
from concurrent.futures._base import CancelledError
import httpx
from datasets import Dataset, DatasetDict
from gradio_client import Client, handle_file
from opencompass.openicl.icl_evaluator import BaseEvaluator
from opencompass.utils import JSONToolkit # noqa: F401, F403
from opencompass.utils import (check_url_accessibility, get_data_path,
get_logger, setup_proxies)
from ..base import BaseDataset
from .extractor import extract_code_generation
class BigCodeBenchDataset(BaseDataset):
@staticmethod
def load(path: str = 'opencompass/bigcodebench',
local_mode: bool = False,
release_version: str = 'v0.1.2',
dataset_version: str = 'full'):
"""
Args:
path (str): The path to the dataset.
local_mode (bool): Whether to use local give path or use
automatically download.
release_version (str): The release version of the dataset.
dataset_version (str): The data version of the dataset.
only support ['full', 'hard']
"""
assert dataset_version in ['full', 'hard'], \
'dataset_version should be one of ["full", "hard"], '
f'but got {dataset_version}'
path = get_data_path(path, local_mode=local_mode)
dataset = DatasetDict()
# Valid Keys:
# 'task_id', 'complete_prompt', 'instruct_prompt',
# 'canonical_solution', 'code_prompt', 'test',
# 'entry_point', 'doc_struct', 'libs'
if dataset_version == 'full':
items = JSONToolkit.read_jsonl(
os.path.join(path, f'BigCodeBench-{release_version}.jsonl'))
else:
items = JSONToolkit.read_jsonl(
os.path.join(path,
f'BigCodeBench-Hard-{release_version}.jsonl'))
dataset['train'] = Dataset.from_list(items)
dataset['test'] = Dataset.from_list(items)
return dataset
class BigCodeBenchEvaluator(BaseEvaluator):
"""Evaluator for BigCodeBench.
Args:
num_process_evaluate (int): number of processes to evaluate
timeout (int): timeout for each evaluation
release_version (str): release version of BigCodeBench
eval_type (str): type of evaluation, either 'instruct' or 'completion'
"""
def __init__(
self,
release_version='v0.1.2',
eval_type='instruct',
remote_execute_api='https://bigcode-bigcodebench-evaluator.hf.space/', # noqa
dataset_version: str = 'full',
pass_k: str = '1,5,10',
parallel: int = -1,
min_time_limit: float = 1,
max_as_limit: int = 30 * 1024,
max_data_limit: int = 30 * 1024,
max_stack_limit: int = 10,
check_gt_only: bool = False,
no_gt: bool = False):
super().__init__()
self.dataset = BigCodeBenchDataset.load(
release_version=release_version,
dataset_version=dataset_version)['test']
self.eval_type = eval_type
self.remote_execute_api = remote_execute_api
self.eval_kwargs = dict(subset=dataset_version,
pass_k=pass_k,
parallel=parallel,
min_time_limit=min_time_limit,
max_as_limit=max_as_limit,
max_data_limit=max_data_limit,
max_stack_limit=max_stack_limit,
check_gt_only=check_gt_only,
no_gt=no_gt)
def score(self, predictions, references):
logger = get_logger()
entrypoints = [item['entry_point'] for item in self.dataset]
# Append content to the end of the prompt for Completion
if self.eval_type == 'complete':
content = [item['complete_prompt'] for item in self.dataset]
predictions = [
content[idx] + item for idx, item in enumerate(predictions)
]
elif self.eval_type == 'instruct':
pass
else:
raise ValueError(f'Unknown eval_type: {self.eval_type}')
# Sanitize predictions for execution
logger.info('Start to extract code from predictions')
sanitized_predictions = []
for prediction, entrypoint in zip(predictions, entrypoints):
sanitized_prediction = extract_code_generation(
prediction, entrypoint=entrypoint)
sanitized_predictions.append(sanitized_prediction)
# Prepare for submission
submitted_contents = []
task_ids = [item['task_id'] for item in self.dataset]
for task_id, sanitized_prediction in zip(task_ids,
sanitized_predictions):
submitted_content = {
'task_id': task_id,
'solution': sanitized_prediction
}
submitted_contents.append(submitted_content)
submitted_contents_path = os.path.join(
self._out_dir, 'bigcodebench_submitted_contents.jsonl')
JSONToolkit.save_jsonl(submitted_contents, submitted_contents_path)
logger.info(f'Dump submitted contents to {submitted_contents_path}')
logger.info(
f'Start to connect to {self.remote_execute_api} for evaluating')
# Conduct evaluation with Eval Client
proxies = setup_proxies('BIGCODEBENCH_EVAL_PROXY_URL')
is_accessible, status_code = check_url_accessibility(
self.remote_execute_api)
if not is_accessible:
logger.error(f'Failed to connect to {self.remote_execute_api} '
f'with status code {status_code}')
return False
while True:
try:
eval_client = Client(self.remote_execute_api,
httpx_kwargs=dict(proxies=proxies))
results, pass_at_k = eval_client.predict(
split=self.eval_type,
samples=handle_file(submitted_contents_path),
api_name='/predict',
**self.eval_kwargs)
break
except (httpx.ReadTimeout, CancelledError):
logger.info('Read timeout error. Retrying in 4s...')
time.sleep(4)
dump_results = {'details': results}
dump_results.update(pass_at_k)
return dump_results

192
opencompass/datasets/bigcodebench/extractor.py Normal file
View File

@ -0,0 +1,192 @@
# Copyright (c) 2024, BigCodeBench and its contributors.
# Copyright (c) 2023, OpenCompass and its contributors.
import ast
import traceback
from typing import Dict, Generator, List, Optional, Set, Tuple
from tree_sitter import Node
from tree_sitter_languages import get_parser
CLASS_TYPE = 'class_definition'
FUNCTION_TYPE = 'function_definition'
IMPORT_TYPE = ['import_statement', 'import_from_statement']
IDENTIFIER_TYPE = 'identifier'
ATTRIBUTE_TYPE = 'attribute'
RETURN_TYPE = 'return_statement'
EXPRESSION_TYPE = 'expression_statement'
ASSIGNMENT_TYPE = 'assignment'
def syntax_check(code, verbose=False):
try:
ast.parse(code)
return True
except (SyntaxError, MemoryError):
if verbose:
traceback.print_exc()
return False
def code_extract(text: str) -> str:
lines = text.split('\n')
longest_line_pair = (0, 0)
longest_so_far = 0
for i in range(len(lines)):
for j in range(i + 1, len(lines)):
current_lines = '\n'.join(lines[i:j + 1])
if syntax_check(current_lines):
current_length = sum(1 for line in lines[i:j + 1]
if line.strip())
if current_length > longest_so_far:
longest_so_far = current_length
longest_line_pair = (i, j)
return '\n'.join(lines[longest_line_pair[0]:longest_line_pair[1] + 1])
def get_deps(nodes: List[Tuple[str, Node]]) -> Dict[str, Set[str]]:
def dfs_get_deps(node: Node, deps: Set[str]) -> None:
for child in node.children:
if child.type == IDENTIFIER_TYPE:
deps.add(child.text.decode('utf8'))
else:
dfs_get_deps(child, deps)
name2deps = {}
for name, node in nodes:
deps = set()
dfs_get_deps(node, deps)
name2deps[name] = deps
return name2deps
def get_function_dependency(entrypoint: str,
call_graph: Dict[str, str]) -> Set[str]:
queue = [entrypoint]
visited = {entrypoint}
while queue:
current = queue.pop(0)
if current not in call_graph:
continue
for neighbour in call_graph[current]:
if not (neighbour in visited):
visited.add(neighbour)
queue.append(neighbour)
return visited
def get_definition_name(node: Node) -> str:
for child in node.children:
if child.type == IDENTIFIER_TYPE:
return child.text.decode('utf8')
def traverse_tree(node: Node) -> Generator[Node, None, None]:
cursor = node.walk()
depth = 0
visited_children = False
while True:
if not visited_children:
yield cursor.node
if not cursor.goto_first_child():
depth += 1
visited_children = True
elif cursor.goto_next_sibling():
visited_children = False
elif not cursor.goto_parent() or depth == 0:
break
else:
depth -= 1
def has_return_statement(node: Node) -> bool:
traverse_nodes = traverse_tree(node)
for node in traverse_nodes:
if node.type == RETURN_TYPE:
return True
return False
def extract_target_code_or_empty(code: str,
entrypoint: Optional[str] = None) -> str:
code = code_extract(code.strip())
code_bytes = bytes(code, 'utf8')
parser = get_parser('python')
tree = parser.parse(code_bytes)
class_names = set()
function_names = set()
variable_names = set()
root_node = tree.root_node
import_nodes = []
definition_nodes = []
for child in root_node.children:
if child.type in IMPORT_TYPE:
import_nodes.append(child)
elif child.type == CLASS_TYPE:
name = get_definition_name(child)
if not (name in class_names or name in variable_names
or name in function_names):
definition_nodes.append((name, child))
class_names.add(name)
elif child.type == FUNCTION_TYPE:
name = get_definition_name(child)
if not (name in function_names or name in variable_names
or name in class_names):
definition_nodes.append((name, child))
function_names.add(get_definition_name(child))
elif (child.type == EXPRESSION_TYPE
and child.children[0].type == ASSIGNMENT_TYPE):
subchild = child.children[0]
name = get_definition_name(subchild)
if not (name in variable_names or name in function_names
or name in class_names):
definition_nodes.append((name, subchild))
variable_names.add(name)
if entrypoint:
name2deps = get_deps(definition_nodes)
reachable = get_function_dependency(entrypoint, name2deps)
sanitized_output = b''
for node in import_nodes:
sanitized_output += code_bytes[node.start_byte:node.end_byte] + b'\n'
for pair in definition_nodes:
name, node = pair
if entrypoint and not (name in reachable):
continue
sanitized_output += code_bytes[node.start_byte:node.end_byte] + b'\n'
sanitized_output = sanitized_output[:-1].decode('utf8')
# ad-hoc approach to remove unnecessary lines, but it works
lines = sanitized_output.splitlines()
outer_lines = []
for i in range(len(lines) - 1, -1, -1):
if lines[i].startswith(' '):
break
if not lines[i].startswith(' ') and entrypoint in lines[i]:
outer_lines.append(i)
if outer_lines:
sanitized_output = '\n'.join(lines[:outer_lines[-1]])
return sanitized_output
def extract_code_generation(model_output: str,
entrypoint: Optional[str] = None):
# Extract code according to the entrypoint
sanitized_code = extract_target_code_or_empty(model_output,
entrypoint).strip()
# Fallback to extract first codeblock if sanitized_code is empty
sanitized_code = code_extract(
model_output) if not sanitized_code else sanitized_code
return sanitized_code

2
opencompass/datasets/cmmlu.py
View File

@ -14,7 +14,7 @@ from .base import BaseDataset
class CMMLUDataset(BaseDataset):
@staticmethod
def load(path: str, name: str):
def load(path: str, name: str, **kwargs):
path = get_data_path(path)
if environ.get('DATASET_SOURCE') == 'ModelScope':
from modelscope import MsDataset

71
opencompass/datasets/generic.py Normal file
View File

@ -0,0 +1,71 @@
import re
def get_final_results(judged_answers, references, origial_responses):
count = 0
is_correct_count = 0
is_incorrect_count = 0
is_not_attempted_count = 0
details = []
for i, j, k in zip(judged_answers, references, origial_responses):
match = re.search(r'(A|B)', i)
grade_letter = match.group(
0) if match else 'B' # Default to "INCORRECT" if no match
detail = {
'pred': k,
'ref': j,
'origin_grade_response': i,
'grade_letter': grade_letter,
'correct': False
}
count += 1
if grade_letter == 'A':
is_correct_count += 1
detail['correct'] = True
elif grade_letter == 'B':
is_incorrect_count += 1
else:
is_not_attempted_count += 1
details.append(detail)
is_correct = is_correct_count / count
is_incorrect = is_incorrect_count / count
# is_not_attempted = is_not_attempted_count / count
is_given_attempted = is_correct + is_incorrect
accuracy_given_attempted = is_correct / is_given_attempted \
if is_given_attempted > 0 else 0
f1 = 2 * accuracy_given_attempted * is_correct / (
accuracy_given_attempted + is_correct) if (accuracy_given_attempted +
is_correct) > 0 else 0
result = {
# 'accuracy_given_attempted': accuracy_given_attempted,
'accuracy': accuracy_given_attempted * 100,
'f1': f1,
'details': details
}
return result
def _generic_llmjudge_postprocess(judgement: str):
match = re.search(r'(A|B)', judgement)
grade_letter = match.group(
0) if match else 'B' # Default to "INCORRECT" if no match
return grade_letter
def generic_llmjudge_postprocess(
output: dict,
output_path: str,
) -> dict:
judged_answers = []
origial_responses = []
references = []
for k, v in output.items():
origial_responses.append(v['prediction'])
processed_judge = _generic_llmjudge_postprocess(v['prediction'])
if processed_judge is not None:
judged_answers.append(processed_judge)
references.append(v['gold'])
results = get_final_results(judged_answers, references, origial_responses)
results['details'] = output
return results

2
opencompass/datasets/gpqa.py
View File

@ -16,7 +16,7 @@ from .base import BaseDataset
class GPQADataset(BaseDataset):
@staticmethod
def load(path: str, name: str):
def load(path: str, name: str, **kwargs):
path = get_data_path(path, local_mode=True)
cnt = 0
data = []

5
opencompass/datasets/humaneval.py
View File

@ -185,6 +185,11 @@ def humaneval_postprocess_v2(text: str) -> str:
text = blocks[0]
return text
def humaneval_postprocess_v3(text: str) -> str:
blocks = re.findall(r'```\w*\n(.*?)```', text, re.DOTALL)
if len(blocks) >= 1:
text = blocks[-1]
return text
def humaneval_internal_v2_postprocess(text: str):
if text.startswith(' ') and not text.startswith(' '):

49
opencompass/datasets/korbench/korbench.py
View File

@ -17,40 +17,40 @@ class korbenchDataset(BaseDataset):
"""Dataset loader for the task in KOR-Bench."""
@staticmethod
def load(path, mode, category):
def load(path, prompt_mode, category, **kwargs):
"""Load the dataset using shared ."""
base_path = get_data_path(path)
rule_file = None
sample_file = None
mixed_file = None
mixed_data = None
if '0_shot' in mode or '3_shot' in mode:
if '0_shot' in prompt_mode or '3_shot' in prompt_mode:
rule_file = find_file(base_path, os.path.join(category, 'rule'))
sample_file = find_file(base_path,
os.path.join(category, 'sample'))
elif mode == 'mixed':
elif prompt_mode == 'mixed':
mixed_file = find_file(base_path, os.path.join('mixed', category))
mixed_data = load_json_or_jsonl(mixed_file) or []
else:
raise ValueError(f'Unsupported mode: {mode}')
raise ValueError(f'Unsupported prompt_mode: {prompt_mode}')
three_shot_file = None
if mode == '3_shot':
if prompt_mode == '3_shot':
ts_path = os.path.join(category, 'three-shot')
three_shot_file = find_file(base_path, ts_path)
# Load data
if mode in ['0_shot', '3_shot']:
if prompt_mode in ['0_shot', '3_shot']:
rules = load_json_or_jsonl(rule_file) or []
samples = load_json_or_jsonl(sample_file) or []
template_path = None
if mode == '0_shot':
if prompt_mode == '0_shot':
template_path = os.path.join(
os.path.dirname(__file__),
'korbench_dataset_config/prompt/0_shot.yaml')
elif mode == '3_shot':
elif prompt_mode == '3_shot':
template_path = os.path.join(
os.path.dirname(__file__),
'korbench_dataset_config/prompt/3_shot.yaml')
elif mode == 'mixed':
elif prompt_mode == 'mixed':
template_path = os.path.join(
os.path.dirname(__file__),
'korbench_dataset_config/prompt/mixed.yaml')
@ -62,7 +62,7 @@ class korbenchDataset(BaseDataset):
# Process data
data = []
if mode == '0_shot':
if prompt_mode == '0_shot':
for sample in samples:
rule_id = sample['rule_id']
rule = next((r for r in rules if r['idx'] == rule_id), None)
@ -81,13 +81,13 @@ class korbenchDataset(BaseDataset):
'answer': sample['answer'],
'prompt': prompt,
'rule_id': rule['idx'],
'mode': '0_shot',
'prompt_mode': '0_shot',
'category': category,
})
return Dataset.from_list(data)
if mode == '3_shot':
if prompt_mode == '3_shot':
data = []
three_shot = load_json_or_jsonl(three_shot_file) or []
for sample in samples:
@ -111,13 +111,13 @@ class korbenchDataset(BaseDataset):
'answer': sample['answer'],
'prompt': prompt,
'rule_id': rule['idx'],
'mode': '3_shot',
'prompt_mode': '3_shot',
'category': category,
})
return Dataset.from_list(data)
if mode == 'mixed':
if prompt_mode == 'mixed':
# Process data
data = []
for item in mixed_data:
@ -159,7 +159,7 @@ class korbenchDataset(BaseDataset):
'rule_list': rule_list,
'question_list': question_list,
'prompt': prompt,
'mode': 'mixed',
'prompt_mode': 'mixed',
'answer': '',
'base_path': base_path,
})
@ -174,14 +174,15 @@ class korbenchEvaluator(BaseEvaluator):
super().__init__()
def score(self, predictions, references, test_set):
"""Evaluate predictions for a single mode in KOR-Bench."""
"""Evaluate predictions for a single prompt_mode in KOR-Bench."""
if not test_set:
raise ValueError('Test set is empty.')
mode = test_set[0]['mode'] # Determine the mode from the first entry
prompt_mode = test_set[0][
'prompt_mode'] # Determine the prompt_mode from the first entry
data = {}
# Organize data for the given mode
# Organize data for the given prompt_mode
for i in range(len(predictions)):
entry = {
'prediction': predictions[i],
@ -195,18 +196,18 @@ class korbenchEvaluator(BaseEvaluator):
data[i] = entry
if not data:
raise ValueError(f"No data found for mode '{mode}'")
raise ValueError(f"No data found for prompt_mode '{prompt_mode}'")
# Evaluate based on the mode
if mode == '0_shot':
# Evaluate based on the prompt_mode
if prompt_mode == '0_shot':
evaluation_results = evaluate_responses(data, '0_shot')
elif mode == '3_shot':
elif prompt_mode == '3_shot':
evaluation_results = evaluate_responses(data, '3_shot')
elif mode in ['Multi-Q', 'Multi-R', 'Multi-RQ', 'mixed']:
elif prompt_mode in ['Multi-Q', 'Multi-R', 'Multi-RQ', 'mixed']:
evaluation_results = evaluate_responses(data, 'mixed',
test_set[0]['base_path'])
else:
raise ValueError(f'Unsupported mode: {mode}')
raise ValueError(f'Unsupported prompt_mode: {prompt_mode}')
# Calculate accuracy
correct_count = sum(res['is_correct'] for res in evaluation_results)
accuracy = (correct_count / len(evaluation_results)) * 100

28
opencompass/datasets/livecodebench/evaluator.py
View File

@ -13,6 +13,7 @@ from opencompass.utils import get_logger
from .execute_utils import BASE_IMPORTS, codeexecute_check_correctness
from .extract_utils import (extract_code_execution, extract_code_generation,
extract_code_generation_v2,
extract_test_output_code)
from .livecodebench import LCBCodeGenerationDataset
from .pass_k_utils import compute_metrics_from_results
@ -231,15 +232,22 @@ class LCBCodeGenerationEvaluator(BaseEvaluator):
def __init__(self,
num_process_evaluate,
timeout=6,
release_version='release_v1'):
release_version='release_v1',
extractor_version='v1'):
super().__init__()
self.num_process_evaluate = num_process_evaluate
self.timeout = timeout
self.dataset = LCBCodeGenerationDataset.load(
release_version=release_version)['test']
self.extractor_version = extractor_version
def score(self, predictions, references):
predictions = [[extract_code_generation(item)] for item in predictions]
if self.extractor_version == 'v1':
predictions = [[extract_code_generation(item)]
for item in predictions]
elif self.extractor_version == 'v2':
predictions = [[extract_code_generation_v2(item)]
for item in predictions]
evaluation_samples = dict()
for idx in range(len(self.dataset)):
@ -252,12 +260,9 @@ class LCBCodeGenerationEvaluator(BaseEvaluator):
BaseEvaluator.is_num_equal(predictions, references)
results = { # noqa: F841
'pass': 0,
'timeout': 0,
'failed': 0,
'wrong_answer': 0
} # noqa: F401, F403
extracted_predictions = {}
for idx, content in enumerate(predictions):
extracted_predictions[idx] = content
metrics, eval_results, final_metadata = codegen_metrics(
references,
@ -266,8 +271,13 @@ class LCBCodeGenerationEvaluator(BaseEvaluator):
num_process_evaluate=self.num_process_evaluate,
timeout=self.timeout,
)
results = {
'extracted_predictions': extracted_predictions,
'eval_results': eval_results
}
results.update(metrics)
return metrics
return results
def evaluate_score(args) -> list[bool]:

20
opencompass/datasets/livecodebench/extract_utils.py
View File

@ -8,6 +8,22 @@ def extract_code_generation(model_output: str, model_type: str = 'chat'):
outputlines = model_output.split('\n')
# TODO: handle codellama
if model_type == 'base':
return model_output.strip()
elif model_type == 'chat':
indexlines = [i for i, line in enumerate(outputlines) if '```' in line]
else:
raise ValueError(f'Invalid mode type: {model_type}')
if len(indexlines) < 2:
return ''
return '\n'.join(outputlines[indexlines[0] + 1:indexlines[1]])
def extract_code_generation_v2(model_output: str, model_type: str = 'chat'):
# modified from
outputlines = model_output.split('\n')
# TODO: handle codellama
if model_type == 'base':
return model_output.strip()
elif model_type == 'chat':
@ -17,6 +33,10 @@ def extract_code_generation(model_output: str, model_type: str = 'chat'):
if len(indexlines) < 2:
return ''
elif len(indexlines) > 2:
# Only Keep the last code block
indexlines = indexlines[-2:]
return '\n'.join(outputlines[indexlines[0] + 1:indexlines[1]])

8
opencompass/datasets/livemathbench/livemathbench.py
View File

@ -12,6 +12,7 @@ from datasets import Dataset
from opencompass.models import OpenAISDK
from opencompass.openicl.icl_evaluator import BaseEvaluator
from opencompass.registry import ICL_EVALUATORS, LOAD_DATASET, MODELS
from opencompass.utils import get_data_path
from ..base import BaseDataset
from .prompts import (EXTRACT_PROMPT_CN, EXTRACT_PROMPT_EN, JUDGE_PROMPT_CN,
@ -31,6 +32,7 @@ class LiveMathBenchDataset(BaseDataset):
) -> List[Dict[str, Any]]:
dataset = []
dataset_info = {}
path = get_data_path(path)
for split, language in product(LiveMathBenchDataset.dataset_splits,
LiveMathBenchDataset.dataset_languages):
file_path = os.path.join(path, f'{split}_{language}.jsonl')
@ -101,10 +103,10 @@ class LiveMathBenchEvaluator(BaseEvaluator):
path=model_name,
openai_api_base=url,
key='EMPTY',
query_per_second=2,
query_per_second=128,
meta_template=self.api_meta_template,
temperature=kwargs.get('temperature', 0.01),
max_seq_len=kwargs.get('max_tokens', 2048),
temperature=kwargs.get('temperature', 0.001),
max_seq_len=kwargs.get('max_tokens', 16384),
)) for url in url
]
self.with_postprocess = with_postprocess

2
opencompass/datasets/livereasonbench/__init__.py Normal file
View File

@ -0,0 +1,2 @@
from .livereasonbench import LiveReasonBenchDataset # noqa: F401, F403
from .livereasonbench import livereasonbench_postprocess # noqa: F401, F403

193
opencompass/datasets/livereasonbench/livereasonbench.py Normal file
View File

@ -0,0 +1,193 @@
# Edited from the official SimpleQA config: https://github.com/openai/simple-evals/blob/main/simpleqa_eval.py # noqa E501
import json
import os
import random
import re
from datasets import Dataset, DatasetDict
from opencompass.registry import LOAD_DATASET
from opencompass.utils import get_data_path
from ..base import BaseDataset
@LOAD_DATASET.register_module()
class LiveReasonBenchDataset(BaseDataset):
@staticmethod
def load(path: str,
num_examples: int | None = None,
n_repeats: int = 1,
version: str = 'livereasonbench-20241202',
**kwargs):
path = get_data_path(path)
dataset = DatasetDict()
# data = read
path = os.path.join(path, f'{version}.json')
with open(path, 'r', encoding='utf-8') as f:
examples = json.load(f)
if num_examples:
assert n_repeats == 1, \
'n_repeats only supported when max_examples = None'
rng = random.Random(0)
examples = rng.sample(examples, num_examples)
examples = examples * n_repeats
dataset['train'] = Dataset.from_list(examples)
dataset['test'] = Dataset.from_list(examples)
return dataset
GRADER_TEMPLATE = """
Your job is to look at a question, a gold target, and a predicted answer, and then assign a grade of either ["CORRECT", "INCORRECT", "NOT_ATTEMPTED"].
First, I will give examples of each grade, and then you will grade a new example.
The following are examples of CORRECT predicted answers.
```
Question: What are the names of Barack Obama's children?
Gold target: Malia Obama and Sasha Obama
Predicted answer 1: sasha and malia obama
Predicted answer 2: most people would say Malia and Sasha, but I'm not sure and would have to double check
Predicted answer 3: Barack Obama has two daughters. Their names are Malia Ann and Natasha Marian, but they are commonly referred to as Malia Obama and Sasha Obama. Malia was born on July 4, 1998, and Sasha was born on June 10, 2001.
```
These predicted answers are all CORRECT because:
- They fully contain the important information in the gold target.
- They do not contain any information that contradicts the gold target.
- Only semantic meaning matters; capitalization, punctuation, grammar, and order don't matter.
- Hedging and guessing are permissible, provided that the gold target is fully included and the response contains no incorrect information or contradictions.
The following are examples of INCORRECT predicted answers.
```
Question: What are the names of Barack Obama's children?
Gold target: Malia and Sasha
Predicted answer 1: Malia.
Predicted answer 2: Malia, Sasha, and Susan.
Predicted answer 3: Barack Obama does not have any children.
Predicted answer 4: I think it's either Malia and Sasha. Or it could be Malia and Jackie. Or it could be Joey and Malia.
Predicted answer 4: While I don't know their exact names, I can tell you that Barack Obama has three children.
Predicted answer 5: It's possible you may mean Betsy and Olivia. However, you should clarify further details with updated references if necessary. Is that the correct answer?
Predicted answer 6: It may be the case that Obama's child is named James. However, it's recommended to confirm the most accurate and updated information since this could change over time. This model may not always reflect the most current information.
```
These predicted answers are all INCORRECT because:
- A factual statement in the answer contradicts the gold target. Incorrect statements that have some hedging (e.g., "it is possible that", "although i'm not sure, i think") are also considered incorrect.
The following are examples of NOT_ATTEMPTED predicted answers.
```
Question: What are the names of Barack Obama's children?
Gold target: Malia and Sasha
Predicted answer 1: I don't know.
Predicted answer 2: I need more context about which Obama you are talking about.
Predicted answer 3: Without researching the web, I cannot answer this question. However, I can tell you that Barack Obama has two children.
Predicted answer 4: Barack Obama has two children. I know that one of them is Malia, but I'm not sure about the other one.
```
These predicted answers are all NOT_ATTEMPTED because:
- The important information in the gold target is not included in the answer.
- No statements in the answer contradict the gold target.
Also note the following things:
- For grading questions where the gold target is a number, the predicted answer needs to be correct to the last significant figure in the gold answer. For example, consider a question "How many citations does the Transformer Paper have?" with gold target "120k".
- Predicted answers "120k", "124k", and 115k" are all CORRECT.
- Predicted answers "100k" and "113k" are INCORRECT.
- Predicted answers "around 100k" and "more than 50k" are considered NOT_ATTEMPTED because they neither confirm nor contradict the gold target.
- The gold target may contain more information than the question. In such cases, the predicted answer only needs to contain the information that is in the question.
- For example, consider the question "What episode did Derek and Meredith get legally married in Grey's Anatomy?" with gold target "Season 7, Episode 20: White Wedding". Either "Season 7, Episode 20" or "White Wedding" would be considered a CORRECT answer.
- Do not punish predicted answers if they omit information that would be clearly inferred from the question.
- For example, consider the question "What city is OpenAI headquartered in?" and the gold target "San Francisco, California". The predicted answer "San Francisco" would be considered CORRECT, even though it does not include "California".
- Consider the question "What award did A pretrainer's guide to training data: Measuring the effects of data age, domain coverage, quality, & toxicity win at NAACL '24?", the gold target is "Outstanding Paper Award". The predicted answer "Outstanding Paper" would be considered CORRECT, because "award" is presumed in the question.
- For the question "What is the height of Jason Wei in meters?", the gold target is "1.73 m". The predicted answer "1.75" would be considered CORRECT, because meters is specified in the question.
- For the question "What is the name of Barack Obama's wife?", the gold target is "Michelle Obama". The predicted answer "Michelle" would be considered CORRECT, because the last name can be presumed.
- Do not punish for typos in people's name if it's clearly the same name.
- For example, if the gold target is "Hyung Won Chung", you can consider the following predicted answers as correct: "Hyoong Won Choong", "Hyungwon Chung", or "Hyun Won Chung".
Grade the predicted answer of this new question as one of:
A: CORRECT
B: INCORRECT
C: NOT_ATTEMPTED
Just return the letters "A", "B", or "C", with no text around it.
Here is a new example. Simply reply with either CORRECT, INCORRECT, NOT ATTEMPTED. Don't apologize or correct yourself if there was a mistake; we are just trying to grade the answer.
```
Question: {question}
Gold target: {gold_answer}
Predicted answer: {answer}
```
""".strip() # noqa E501
api_meta_template = dict(round=[
dict(role='HUMAN', api_role='HUMAN'),
dict(role='BOT', api_role='BOT', generate=True),
])
def get_final_results(judged_answers, references, origial_responses):
count = 0
is_correct_count = 0
is_incorrect_count = 0
is_not_attempted_count = 0
details = []
for i, j, k in zip(judged_answers, references, origial_responses):
match = re.search(r'(A|B|C)', i)
grade_letter = match.group(
0) if match else 'C' # Default to "NOT_ATTEMPTED" if no match
detail = {
'pred': k,
'ref': j,
'origin_grade_response': i,
'grade_letter': grade_letter,
'correct': False
}
count += 1
if grade_letter == 'A':
is_correct_count += 1
detail['correct'] = True
elif grade_letter == 'B':
is_incorrect_count += 1
else:
is_not_attempted_count += 1
details.append(detail)
is_correct = is_correct_count / count
is_incorrect = is_incorrect_count / count
# is_not_attempted = is_not_attempted_count / count
is_given_attempted = is_correct + is_incorrect
accuracy_given_attempted = is_correct / is_given_attempted \
if is_given_attempted > 0 else 0
f1 = 2 * accuracy_given_attempted * is_correct / (
accuracy_given_attempted + is_correct) if (accuracy_given_attempted +
is_correct) > 0 else 0
result = {
'accuracy_given_attempted': accuracy_given_attempted,
'f1': f1,
'details': details
}
return result
def _livereasonbench_postprocess(judgement: str):
match = re.search(r'(A|B|C)', judgement)
grade_letter = match.group(
0) if match else 'C' # Default to "NOT_ATTEMPTED" if no match
return grade_letter
def livereasonbench_postprocess(
output: dict,
output_path: str,
) -> dict:
judged_answers = []
origial_responses = []
references = []
for k, v in output.items():
origial_responses.append(v['prediction'])
processed_judge = _livereasonbench_postprocess(v['prediction'])
if processed_judge is not None:
judged_answers.append(processed_judge)
references.append(v['gold'])
results = get_final_results(judged_answers, references, origial_responses)
results['details'] = output
return results

2
opencompass/datasets/math.py
View File

@ -141,7 +141,7 @@ def extract_answer(response_text: str):
class MATHDataset(BaseDataset):
@staticmethod
def load(path: str, file_name: str = 'math.json'):
def load(path: str, file_name: str = 'math.json', **kwargs):
path = get_data_path(path)
dataset = DatasetDict()
raw_data = []

2
opencompass/datasets/mmlu.py
View File

@ -15,7 +15,7 @@ from .base import BaseDataset
class MMLUDataset(BaseDataset):
@staticmethod
def load(path: str, name: str):
def load(path: str, name: str, **kwargs):
path = get_data_path(path)
dataset = DatasetDict()
if environ.get('DATASET_SOURCE') == 'ModelScope':

13
opencompass/models/openai_api.py
View File

@ -9,6 +9,7 @@ from typing import Dict, List, Optional, Union
import httpx
import jieba
import requests
from tqdm import tqdm
from opencompass.registry import MODELS
from opencompass.utils.prompt import PromptList
@ -19,6 +20,8 @@ PromptType = Union[PromptList, str]
OPENAI_API_BASE = os.path.join(
os.environ.get('OPENAI_BASE_URL', 'https://api.openai.com/v1/'),
'chat/completions')
OPENAISDK_API_BASE = os.environ.get('OPENAI_BASE_URL',
'https://api.openai.com/v1/')
O1_MODEL_LIST = [
'o1-preview-2024-09-12',
@ -170,9 +173,11 @@ class OpenAI(BaseAPIModel):
with ThreadPoolExecutor() as executor:
results = list(
executor.map(self._generate, inputs,
[max_out_len] * len(inputs),
[temperature] * len(inputs)))
tqdm(executor.map(self._generate, inputs,
[max_out_len] * len(inputs),
[temperature] * len(inputs)),
total=len(inputs),
desc='Inferencing'))
return results
def _generate(self, input: PromptType, max_out_len: int,
@ -476,7 +481,7 @@ class OpenAISDK(OpenAI):
key: str | List[str] = 'ENV',
org: str | List[str] | None = None,
meta_template: Dict | None = None,
openai_api_base: str = OPENAI_API_BASE,
openai_api_base: str = OPENAISDK_API_BASE,
openai_proxy_url: Optional[str] = None,
mode: str = 'none',
logprobs: bool | None = False,

34
opencompass/tasks/base.py
View File

@ -1,13 +1,45 @@
import copy
import os
import re
from abc import abstractmethod
from typing import List
from typing import List, Optional
from mmengine.config import ConfigDict
from opencompass.utils import get_infer_output_path, task_abbr_from_cfg
def extract_role_pred(s: str, begin_str: Optional[str],
end_str: Optional[str]) -> str:
"""Extract the role prediction from the full prediction string. The role
prediction may be the substring between the begin and end string.
Args:
s (str): Full prediction string.
begin_str (str): The beginning string of the role
end_str (str): The ending string of the role.
Returns:
str: The extracted role prediction.
"""
start = 0
end = len(s)
if begin_str and re.match(r'\s*', begin_str) is None:
begin_idx = s.find(begin_str)
if begin_idx != -1:
start = begin_idx + len(begin_str)
if end_str and re.match(r'\s*', end_str) is None:
# TODO: Support calling tokenizer for the accurate eos token
# and avoid such hardcode
end_idx = s.find(end_str, start)
if end_idx != -1:
end = end_idx
return s[start:end]
class BaseTask:
"""Base class for all tasks. There are two ways to run the task:
1. Directly by calling the `run` method.

36
opencompass/tasks/openicl_eval.py
View File

@ -4,13 +4,12 @@ import fnmatch
import math
import os
import os.path as osp
import re
import statistics
import sys
import time
from collections import Counter
from inspect import signature
from typing import List, Optional
from typing import List
import mmengine
from mmengine.config import Config, ConfigDict
@ -18,43 +17,12 @@ from mmengine.utils import mkdir_or_exist
from opencompass.registry import (ICL_EVALUATORS, MODELS, TASKS,
TEXT_POSTPROCESSORS)
from opencompass.tasks.base import BaseTask
from opencompass.tasks.base import BaseTask, extract_role_pred
from opencompass.utils import (build_dataset_from_cfg, dataset_abbr_from_cfg,
get_infer_output_path, get_logger,
task_abbr_from_cfg)
def extract_role_pred(s: str, begin_str: Optional[str],
end_str: Optional[str]) -> str:
"""Extract the role prediction from the full prediction string. The role
prediction may be the substring between the begin and end string.
Args:
s (str): Full prediction string.
begin_str (str): The beginning string of the role
end_str (str): The ending string of the role.
Returns:
str: The extracted role prediction.
"""
start = 0
end = len(s)
if begin_str and re.match(r'\s*', begin_str) is None:
begin_idx = s.find(begin_str)
if begin_idx != -1:
start = begin_idx + len(begin_str)
if end_str and re.match(r'\s*', end_str) is None:
# TODO: Support calling tokenizer for the accurate eos token
# and avoid such hardcode
end_idx = s.find(end_str, start)
if end_idx != -1:
end = end_idx
return s[start:end]
@TASKS.register_module()
class OpenICLEvalTask(BaseTask):
"""OpenICL Evaluation Task.

3
opencompass/tasks/subjective_eval.py
View File

@ -12,8 +12,7 @@ from mmengine.config import Config, ConfigDict
from mmengine.utils import mkdir_or_exist
from opencompass.registry import ICL_EVALUATORS, MODELS, TEXT_POSTPROCESSORS
from opencompass.tasks.base import BaseTask
from opencompass.tasks.openicl_eval import extract_role_pred
from opencompass.tasks.base import BaseTask, extract_role_pred
from opencompass.utils import (build_dataset_from_cfg, dataset_abbr_from_cfg,
deal_with_judge_model_abbr, get_data_path,
get_infer_output_path, get_logger,

1
opencompass/utils/__init__.py
View File

@ -11,6 +11,7 @@ from .lark import * # noqa
from .logging import * # noqa
from .menu import * # noqa
from .model_postprocessors import * # noqa
from .network import * # noqa
from .postprocessors import * # noqa
from .prompt import * # noqa
from .text_postprocessors import * # noqa

23
opencompass/utils/datasets_info.py
View File

@ -357,6 +357,21 @@ DATASETS_MAPPING = {
"ms_id": "",
"hf_id": "",
"local": "./data/simpleqa/simple_qa_test_set.csv",
},
"opencompass/LiveMathBench202412": {
"ms_id": "",
"hf_id": "",
"local": "./data/LiveMathBench/",
},
"opencompass/LiveReasonBench": {
"ms_id": "",
"hf_id": "",
"local": "./data/LiveReasonBench/",
},
"opencompass/bigcodebench": {
"ms_id": "",
"hf_id": "",
"local": "./data/bigcodebench/",
}
}
@ -584,5 +599,13 @@ DATASETS_URL = {
"P-MMEval": {
"url": "http://opencompass.oss-cn-shanghai.aliyuncs.com/datasets/data/pmmeval.zip",
"md5": "09e401e6229a50647b9e13c429e634d1",
},
"LiveMathBench": {
'url': "http://opencompass.oss-cn-shanghai.aliyuncs.com/datasets/data/LiveMathBench.zip",
"md5": "789df4604260d5cf3ba7a891077cf6a0",
},
"bigcodebench": {
"url": "http://opencompass.oss-cn-shanghai.aliyuncs.com/datasets/data/bigcodebench.zip",
"md5": "2c1c7956ca49a1124617e8c037ec57d8"
}
}

147
opencompass/utils/fileio.py
View File

@ -1,6 +1,7 @@
import gzip
import hashlib
import io
import json
import os
import os.path
import shutil
@ -10,10 +11,156 @@ import urllib.error
import urllib.request
import zipfile
from contextlib import contextmanager
from pathlib import Path
from typing import Any, Dict, List, Optional, Union
import mmengine.fileio as fileio
from mmengine.fileio import LocalBackend, get_file_backend
from .logging import get_logger
logger = get_logger()
class JSONToolkit:
"""A toolkit for handling JSON and JSONL file operations."""
@staticmethod
def read_json(file_path: Union[str, Path]) -> Dict[str, Any]:
"""Read a JSON file and return its contents as a dictionary.
Args:
file_path: Path to the JSON file
Returns:
Dictionary containing the JSON data
Raises:
FileNotFoundError: If the file doesn't exist
json.JSONDecodeError: If the file contains invalid JSON
"""
file_path = Path(file_path)
try:
with file_path.open('r', encoding='utf-8') as f:
return json.load(f)
except FileNotFoundError:
logger.error(f'File not found: {file_path}')
raise
except json.JSONDecodeError as e:
logger.error(f'Invalid JSON in file {file_path}: {str(e)}')
raise
@staticmethod
def read_jsonl(file_path: Union[str, Path]) -> List[Dict[str, Any]]:
"""Read a JSONL file and return its contents as a list of dictionaries.
Args:
file_path: Path to the JSONL file
Returns:
List of dictionaries, each representing a JSON line
Raises:
FileNotFoundError: If the file doesn't exist
json.JSONDecodeError: If any line contains invalid JSON
"""
file_path = Path(file_path)
results = []
try:
with file_path.open('r', encoding='utf-8') as f:
for line_num, line in enumerate(f, 1):
line = line.strip()
if not line: # Skip empty lines
continue
try:
results.append(json.loads(line))
except json.JSONDecodeError as e:
logger.error(
f'Invalid JSON on line {line_num}: {str(e)}')
raise
except FileNotFoundError:
logger.error(f'File not found: {file_path}')
raise
return results
@staticmethod
def save_json(data: Dict[str, Any],
file_path: Union[str, Path],
indent: Optional[int] = 2) -> None:
"""Save a dictionary as a JSON file.
Args:
data: Dictionary to save
file_path: Path where to save the JSON file
indent: Number of spaces for indentation
(None for no pretty printing)
Raises:
TypeError: If data is not JSON serializable
"""
file_path = Path(file_path)
file_path.parent.mkdir(parents=True, exist_ok=True)
try:
with file_path.open('w', encoding='utf-8') as f:
json.dump(data, f, indent=indent, ensure_ascii=False)
logger.info(f'Successfully saved JSON to {file_path}')
except TypeError as e:
logger.error(f'Data is not JSON serializable: {str(e)}')
raise
@staticmethod
def save_jsonl(data: List[Dict[str, Any]], file_path: Union[str,
Path]) -> None:
"""Save a list of dictionaries as a JSONL file.
Args:
data: List of dictionaries to save
file_path: Path where to save the JSONL file
Raises:
TypeError: If any item in data is not JSON serializable
"""
file_path = Path(file_path)
file_path.parent.mkdir(parents=True, exist_ok=True)
try:
with file_path.open('w', encoding='utf-8') as f:
for item in data:
json_line = json.dumps(item, ensure_ascii=False)
f.write(json_line + '\n')
logger.info(f'Successfully saved JSONL to {file_path}')
except TypeError as e:
logger.error(f'Data is not JSON serializable: {str(e)}')
raise
@staticmethod
@contextmanager
def jsonl_writer(file_path: Union[str, Path]):
"""Context manager for writing JSONL files line by line.
Args:
file_path: Path where to save the JSONL file
Yields:
Function to write individual JSON lines
"""
file_path = Path(file_path)
file_path.parent.mkdir(parents=True, exist_ok=True)
def write_line(data: Dict[str, Any]):
nonlocal f
json_line = json.dumps(data, ensure_ascii=False)
f.write(json_line + '\n')
try:
with file_path.open('w', encoding='utf-8') as f:
yield write_line
logger.info(f'Successfully saved JSONL to {file_path}')
except TypeError as e:
logger.error(f'Data is not JSON serializable: {str(e)}')
raise
def patch_func(module, fn_name_to_wrap):
backup = getattr(patch_func, '_backup', [])

142
opencompass/utils/network.py Normal file
View File

@ -0,0 +1,142 @@
import os
import platform
import socket
import subprocess
from typing import Dict, Optional, Tuple
import requests
from .logging import get_logger
logger = get_logger()
def setup_proxies(proxy_env_name):
try:
proxy_url = os.environ[proxy_env_name]
if not proxy_url:
raise ValueError('Proxy URL environment variable is empty')
# Validate proxy URL format
if not proxy_url.startswith(('http://', 'https://')):
raise ValueError('Proxy URL must start with http:// or https://')
proxies = {'http://': proxy_url, 'https://': proxy_url}
return proxies
except KeyError:
# Handle the proxy_env_name environment is nonexistent
logger.warning(f'{proxy_env_name} environment variable not found')
return {}
except ValueError as e:
# Handle invalid proxy URL format
logger.error(f'Invalid proxy configuration: {str(e)}')
return None
except Exception as e:
# Handle any unexpected errors
logger.error(f'Unexpected error while setting up proxies: {str(e)}')
return None
def check_network_connectivity(
host: str = '8.8.8.8',
port: int = 53,
timeout: float = 3,
proxies: Optional[Dict[str, str]] = None) -> Tuple[bool, str]:
"""Check network connectivity using multiple methods with optional proxy
support.
Args:
host: str, target host to check (default: Google DNS "8.8.8.8")
port: int, target port to check (default: 53 for DNS)
timeout: float, timeout in seconds (default: 3)
proxies: Optional[Dict[str, str]], proxy configuration (default: None)
Example: {
'http': 'http://proxy:8080',
'https': 'https://proxy:8080'
}
Returns:
Tuple[bool, str]: (is_connected, message)
"""
# Method 1: Socket connection test (direct connection, no proxy)
def check_socket() -> bool:
try:
socket.create_connection((host, port), timeout=timeout)
return True
except OSError:
return False
# Method 2: HTTP request test (supports proxy)
def check_http() -> bool:
try:
response = requests.get('http://www.google.com',
timeout=timeout,
proxies=proxies)
return response.status_code == 200
except requests.RequestException:
return False
# Method 3: Ping test (direct connection, no proxy)
def check_ping() -> bool:
param = '-n' if platform.system().lower() == 'windows' else '-c'
command = ['ping', param, '1', host]
try:
return subprocess.call(command,
stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULL) == 0
except subprocess.SubprocessError:
return False
# Try all methods
is_socket_connected = check_socket()
is_http_connected = check_http()
is_ping_connected = check_ping()
# Generate detailed message including proxy information
status_msg = (
f'Network Status:\n'
f"Socket Test: {'Success' if is_socket_connected else 'Failed'}\n"
f"HTTP Test (via {'Proxy' if proxies else 'Direct'}): "
f"{'Success' if is_http_connected else 'Failed'}\n"
f"Ping Test: {'Success' if is_ping_connected else 'Failed'}")
# If using proxy, add proxy details to message
if proxies:
status_msg += '\nProxy Configuration:'
for protocol, proxy in proxies.items():
status_msg += f'\n {protocol}: {proxy}'
is_connected = any(
[is_socket_connected, is_http_connected, is_ping_connected])
logger.info(status_msg)
return is_connected, status_msg
def check_url_accessibility(
url: str,
timeout: float = 3,
proxies: Optional[Dict[str,
str]] = None) -> Tuple[bool, Optional[int]]:
"""Check if a specific URL is accessible through optional proxy.
Args:
url: str, target URL to check
timeout: float, timeout in seconds (default: 3)
proxies: Optional[Dict[str, str]], proxy configuration (default: None)
Example: {
'http': 'http://proxy:8080',
'https': 'https://proxy:8080'}
Returns:
Tuple[bool, Optional[int]]: (is_accessible, status_code)
"""
try:
response = requests.get(url, timeout=timeout, proxies=proxies)
return True, response.status_code
except requests.RequestException as e:
logger.error(f'Failed to access URL {url}: {str(e)}')
return False, None

4
requirements/runtime.txt
View File

@ -6,12 +6,14 @@ einops==0.5.0
evaluate>=0.3.0
func_timeout
fuzzywuzzy
gradio-client
h5py
huggingface_hub<=0.24.7
immutabledict
importlib-metadata
jieba
json5
jsonlines
mmengine-lite
nltk==3.8
numpy>=1.23.4,<2.0.0
@ -42,4 +44,6 @@ tokenizers>=0.13.3
torch>=1.13.1
tqdm>=4.64.1
transformers>=4.29.1
tree-sitter==0.21.3
tree_sitter_languages>=1.10.2
typer