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

Merge branch 'main' of github.com:open-compass/opencompass into tmp_olmpbench

Browse Source
This commit is contained in:
liushz 2025-02-26 06:36:47 +00:00
commit e2884667b4
18 changed files with 615 additions and 64 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
examples/eval_simpleqa.py
View File

@ -36,8 +36,8 @@ infer = dict(
eval = dict(
partitioner=dict(
type=SubjectiveNaivePartitioner,
models=[gpt_4o_2024_05_13_model],
judge_models=[gpt_4o_2024_05_13_model],
models=models,
judge_models=judge_models,
),
runner=dict(type=LocalRunner,
max_num_workers=256,

2
opencompass/cli/main.py
View File

@ -177,8 +177,6 @@ def parse_dlc_args(dlc_parser):
type=str)
def parse_hf_args(hf_parser):
"""These args are all for the quick construction of HuggingFace models."""
hf_parser.add_argument('--hf-type', type=str, choices=['base', 'chat'], default='chat', help='The type of the HuggingFace model, base or chat')

109
opencompass/configs/datasets/OlympiadBench/OlympiadBench_0shot_llmverify_gen_be8b13.py Normal file
View File

@ -0,0 +1,109 @@
from mmengine.config import read_base
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import OlympiadBenchDataset, OlympiadBenchEvaluator, olympiadbench_postprocess_v2
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.evaluator import GenericLLMEvaluator
from opencompass.datasets import generic_llmjudge_postprocess
with read_base():
from .OlympiadBench_categories import categories
# Create prompter instance for problems
olympiadbench_prompter_cfg = dict(
type='OlympiadBenchPrompter'
)
olympiadbench_reader_cfg = dict(
input_columns=[
'problem', 'language', 'subject', 'question_type',
'answer_type', 'is_multiple_answer', 'unit', 'questions'
],
output_column='solution'
)
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{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()
olympiadbench_datasets = []
for _name in categories:
olympiadbench_infer_cfg = dict(
prompt_template=dict(
type='OlympiadBenchTemplate'
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer),
)
# olympiadbench_eval_cfg = dict(
# evaluator=dict(type=OlympiadBenchEvaluator, version='v2'),
# pred_postprocessor=dict(type=olympiadbench_postprocess_v2),
# )
# Evaluation configuration
olympiadbench_eval_cfg = dict(
evaluator=dict(
type=GenericLLMEvaluator,
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
),
]),
),
dataset_cfg=dict(
type=OlympiadBenchDataset,
path='opencompass/OlympiadBench',
name=_name,
reader_cfg=olympiadbench_reader_cfg,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
pred_role='BOT',
)
olympiadbench_datasets.append(
dict(
type=OlympiadBenchDataset,
abbr=f'OlympiadBench_{_name}',
path='opencompass/OlympiadBench',
name=_name,
reader_cfg=olympiadbench_reader_cfg,
infer_cfg=olympiadbench_infer_cfg,
eval_cfg=olympiadbench_eval_cfg,
)
)
del _name

96
opencompass/configs/datasets/aime2024/aime2024_llmverify_repeat16_gen_bf7475.py Normal file
View File

@ -0,0 +1,96 @@
# CoT: No CoT
# K-Shot: 0-Shot
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.evaluator import GenericLLMEvaluator
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)
)
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=GenericLLMEvaluator,
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
),
]),
),
dataset_cfg=dict(
type=Aime2024Dataset,
path='opencompass/aime2024',
reader_cfg=aime2024_reader_cfg,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
pred_role='BOT',
)
aime2024_datasets = [
dict(
abbr=f'aime2024-run{idx}',
type=Aime2024Dataset,
path='opencompass/aime2024',
reader_cfg=aime2024_reader_cfg,
infer_cfg=aime2024_infer_cfg,
eval_cfg=aime2024_eval_cfg,
mode='singlescore',
)
for idx in range(16)
]

96
opencompass/configs/datasets/aime2024/aime2024_llmverify_repeat8_gen_e8fcee.py Normal file
View File

@ -0,0 +1,96 @@
# CoT: No CoT
# K-Shot: 0-Shot
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.evaluator import GenericLLMEvaluator
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)
)
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=GenericLLMEvaluator,
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
),
]),
),
dataset_cfg=dict(
type=Aime2024Dataset,
path='opencompass/aime2024',
reader_cfg=aime2024_reader_cfg,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
pred_role='BOT',
)
aime2024_datasets = [
dict(
abbr=f'aime2024-run{idx}',
type=Aime2024Dataset,
path='opencompass/aime2024',
reader_cfg=aime2024_reader_cfg,
infer_cfg=aime2024_infer_cfg,
eval_cfg=aime2024_eval_cfg,
mode='singlescore',
)
for idx in range(8)
]

2
opencompass/configs/datasets/livemathbench/livemathbench_gen_9befbf.py
View File

@ -48,4 +48,4 @@ livemathbench_dataset = dict(
)
)
)
livemathbench_datasets = [livemathbench_dataset]
livemathbench_datasets = [livemathbench_dataset]

49
opencompass/configs/datasets/livemathbench/livemathbench_gen_f1c095.py
View File

@ -1,49 +0,0 @@
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.livemathbench import LiveMathBenchDataset, LiveMathBenchEvaluator
livemathbench_reader_cfg = dict(
input_columns=['prompt'],
output_column='answer'
)
livemathbench_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN', prompt='{prompt}'),
]
)
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(
type=GenInferencer,
max_out_len=8192,
temperature=1.0
)
)
livemathbench_eval_cfg = dict(
evaluator=dict(
type=LiveMathBenchEvaluator,
model_name='Qwen/Qwen2.5-72B-Instruct',
url=['http://172.30.40.154:23333/v1/'] #'https://api.openai.com/v1/'
)
)
livemathbench_datasets = [
dict(
type=LiveMathBenchDataset,
abbr='LiveMathBench-k1-n1',
path='opencompass/LiveMathBench202412',
k=1, # K@Pass
n=1, # Run times
reader_cfg=livemathbench_reader_cfg,
infer_cfg=livemathbench_infer_cfg,
eval_cfg=livemathbench_eval_cfg
)
]

2
opencompass/configs/datasets/livemathbench/livemathbench_greedy_gen.py
View File

@ -1,4 +1,4 @@
from mmengine.config import read_base
with read_base():
from .livemathbench_greedy_gen_efb20d import livemathbench_datasets # noqa: F401, F403
from .livemathbench_greedy_gen_9befbf import livemathbench_datasets # noqa: F401, F403

50
opencompass/configs/datasets/livemathbench/livemathbench_hard_gen_353ae7.py Normal file
View File

@ -0,0 +1,50 @@
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.livemathbench import LiveMathBenchDataset, LiveMathBenchEvaluator
livemathbench_dataset = dict(
type=LiveMathBenchDataset,
path='',
k=16,
replication=3,
dataset_splits=['hard'],
dataset_languages=['cn', 'en'],
cot=True,
version='202412',
abbr='LiveMathBench-v202412-Hard',
reader_cfg=dict(
input_columns=['prompt'],
output_column='answer'
),
infer_cfg=dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN', prompt='{prompt}'),
]
)
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(
type=GenInferencer
),
),
eval_cfg=dict(
evaluator=dict(
type=LiveMathBenchEvaluator,
model_name='',
url=[],
use_extract_model=False,
extract_url=[],
extract_model_name='',
k=[4, 8, 16],
replication=3,
thresholds=[0.0, 0.25, 0.5, 0.75, 1.0]
)
)
)
livemathbench_datasets = [livemathbench_dataset]

50
opencompass/configs/datasets/livemathbench/livemathbench_hard_greedy_gen_353ae7.py Normal file
View File

@ -0,0 +1,50 @@
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.livemathbench import LiveMathBenchDataset, LiveMathBenchEvaluator
livemathbench_dataset = dict(
type=LiveMathBenchDataset,
path='',
k=1,
replication=1,
dataset_splits=['hard'],
dataset_languages=['cn', 'en'],
cot=True,
version='202412',
abbr='LiveMathBench-v202412-Hard',
reader_cfg=dict(
input_columns=['prompt'],
output_column='answer'
),
infer_cfg=dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN', prompt='{prompt}'),
]
)
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(
type=GenInferencer
),
),
eval_cfg=dict(
evaluator=dict(
type=LiveMathBenchEvaluator,
model_name='',
url=[],
use_extract_model=False,
extract_url=[],
extract_model_name='',
k=[1],
replication=1,
thresholds=[0.0]
)
)
)
livemathbench_datasets = [livemathbench_dataset]

99
opencompass/configs/datasets/math/math_prm800k_500_llmverify_gen_6ff468.py Normal file
View File

@ -0,0 +1,99 @@
# CoT: No CoT
# K-Shot: 0-Shot
# Verify: LLM Verify
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.evaluator import GenericLLMEvaluator
from opencompass.datasets import generic_llmjudge_postprocess
from opencompass.datasets import MATHDataset
# ----------------------------- Detailed Config -----------------------------
math_reader_cfg = dict(input_columns=['problem'], output_column='solution')
math_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN', prompt='{problem}\nRemember to put your final answer within \\boxed{}.'),
]
),
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer),
)
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{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()
# Evaluation configuration
math_eval_cfg = dict(
evaluator=dict(
type=GenericLLMEvaluator,
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
),
]),
),
dataset_cfg=dict(
type=MATHDataset,
path='opencompass/math',
file_name = 'test_prm800k_500.json',
reader_cfg=math_reader_cfg,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
pred_role='BOT',
)
math_datasets = [
dict(
type=MATHDataset,
abbr='math_prm800k_500-llmjudge',
path='opencompass/math',
file_name = 'test_prm800k_500.json',
reader_cfg=math_reader_cfg,
infer_cfg=math_infer_cfg,
eval_cfg=math_eval_cfg,
mode='singlescore',
)
]

100
opencompass/configs/datasets/math/math_prm800k_500_llmverify_repeat4_gen_97b203.py Normal file
View File

@ -0,0 +1,100 @@
# CoT: No CoT
# K-Shot: 0-Shot
# Verify: LLM Verify
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.evaluator import GenericLLMEvaluator
from opencompass.datasets import generic_llmjudge_postprocess
from opencompass.datasets import MATHDataset
# ----------------------------- Detailed Config -----------------------------
math_reader_cfg = dict(input_columns=['problem'], output_column='solution')
math_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN', prompt='{problem}\nRemember to put your final answer within \\boxed{}.'),
]
),
),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer),
)
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{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()
# Evaluation configuration
math_eval_cfg = dict(
evaluator=dict(
type=GenericLLMEvaluator,
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
),
]),
),
dataset_cfg=dict(
type=MATHDataset,
path='opencompass/math',
file_name = 'test_prm800k_500.json',
reader_cfg=math_reader_cfg,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_postprocess),
),
pred_role='BOT',
)
math_datasets = [
dict(
type=MATHDataset,
abbr=f'math_prm800k_500-llmjudge-run{idx}',
path='opencompass/math',
file_name = 'test_prm800k_500.json',
reader_cfg=math_reader_cfg,
infer_cfg=math_infer_cfg,
eval_cfg=math_eval_cfg,
mode='singlescore',
)
for idx in range(4)
]

3
opencompass/datasets/base.py
View File

@ -1,4 +1,3 @@
from abc import abstractstaticmethod
from typing import Dict, Optional, Union
from datasets import Dataset, DatasetDict
@ -23,6 +22,6 @@ class BaseDataset:
def test(self):
return self.reader.dataset['test']
@abstractstaticmethod
@staticmethod
def load(**kwargs) -> Union[Dataset, DatasetDict]:
pass

2
opencompass/datasets/livemathbench/livemathbench.py
View File

@ -48,6 +48,7 @@ class LiveMathBenchDataset(BaseDataset):
if path != '':
path = get_data_path(path)
path = os.path.join(path, version)
for split, language in product(dataset_splits, dataset_languages):
dataset_info[f'{split}_{language}'] = {
'single-choice': 0,
@ -64,7 +65,6 @@ class LiveMathBenchDataset(BaseDataset):
if path != '':
file_path = os.path.join(path, f'{split}_{language}.jsonl')
if not os.path.exists(file_path):
raise FileNotFoundError(
f'File {file_path} does not exist, please check the '

2
opencompass/models/turbomind_with_tf_above_v4_33.py
View File

@ -164,8 +164,6 @@ class TurboMindModelwithChatTemplate(BaseModel):
self.logger.info('Generation Config of LMdeploy: ')
self.logger.info(gen_config)
results = []
outputs = self.pipe(messages, gen_config=gen_config, do_preprocess=False)
for output in outputs:

3
opencompass/openicl/icl_retriever/icl_topk_retriever.py
View File

@ -7,7 +7,6 @@ from typing import Any, Dict, List, Optional, Union
import numpy as np
import torch
import tqdm
from sentence_transformers import SentenceTransformer
from torch.utils.data import DataLoader
from transformers import AutoTokenizer, BatchEncoding, PreTrainedTokenizerBase
from transformers.file_utils import PaddingStrategy
@ -56,6 +55,8 @@ class TopkRetriever(BaseRetriever):
tokenizer_name: Optional[str] = 'gpt2-xl',
batch_size: Optional[int] = 1) -> None:
super().__init__(dataset, ice_separator, ice_eos_token, ice_num)
from sentence_transformers import SentenceTransformer
self.device = 'cuda' if torch.cuda.is_available() else 'cpu'
self.batch_size = batch_size
self.tokenizer_name = tokenizer_name

2
requirements/runtime.txt
View File

@ -9,7 +9,7 @@ fuzzywuzzy
gradio-client
h5py
httpx==0.27.2
huggingface_hub<=0.24.7
huggingface_hub
immutabledict
importlib-metadata
jieba

8
tools/list_configs.py
View File

@ -19,11 +19,15 @@ def parse_args():
def main():
args = parse_args()
models = match_files('configs/models/', args.pattern, fuzzy=True)
models = match_files('opencompass/configs/models/',
args.pattern,
fuzzy=True)
if models:
table = [['Model', 'Config Path'], *models]
print(tabulate.tabulate(table, headers='firstrow', tablefmt='psql'))
datasets = match_files('configs/datasets/', args.pattern, fuzzy=True)
datasets = match_files('opencompass/configs/datasets/',
args.pattern,
fuzzy=True)
if datasets:
table = [['Dataset', 'Config Path'], *datasets]
print(tabulate.tabulate(table, headers='firstrow', tablefmt='psql'))