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] Academic bench llm judge update (#1876)

Browse Source 
* BigCodeBench update

* update LCBench

* update LCBench 2

* update code

* academicBench update

* academic bench ifeval&math update

* generic_llmjudge_aime_academic_postprocess delete

* aime delete

* postprocessors update

* ifeval delete

* update work_dir

* linting

* linting double-quote-string-fixer

* r1-distill out_len update

* fix lint

---------

Co-authored-by: MaiziXiao <xxllcc1993@gmail.com>
This commit is contained in:
Dongsheng Zhu 2025-02-24 15:45:24 +08:00 committed by GitHub
parent 046b6f75c6
commit 465e93e10e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
17 changed files with 755 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

137
examples/eval_academic_leaderboard_202502.py Normal file
View File

@ -0,0 +1,137 @@
# flake8: noqa
from mmengine.config import read_base
from opencompass.partitioners import NaivePartitioner, NumWorkerPartitioner
from opencompass.runners import LocalRunner, VOLCRunner
from opencompass.tasks import OpenICLEvalTask, OpenICLInferTask
#######################################################################
# PART 0 Essential Configs #
#######################################################################
with read_base():
# Datasets Part
# Knowledge
# Math
from opencompass.configs.datasets.aime2024.aime2024_0shot_nocot_genericllmeval_academic_gen import \
aime2024_datasets
from opencompass.configs.datasets.bbh.bbh_0shot_nocot_academic_gen import \
bbh_datasets
# General Reasoning
from opencompass.configs.datasets.gpqa.gpqa_openai_simple_evals_gen_5aeece import \
gpqa_datasets
from opencompass.configs.datasets.humaneval.humaneval_openai_sample_evals_gen_dcae0e import \
humaneval_datasets
# Instruction Following
from opencompass.configs.datasets.IFEval.IFEval_gen_353ae7 import \
ifeval_datasets
from opencompass.configs.datasets.livecodebench.livecodebench_gen_a4f90b import \
LCBCodeGeneration_dataset
from opencompass.configs.datasets.math.math_prm800k_500_0shot_cot_gen import \
math_datasets
from opencompass.configs.datasets.mmlu_pro.mmlu_pro_0shot_cot_gen_08c1de import \
mmlu_pro_datasets
# Model List
from opencompass.configs.models.hf_internlm.lmdeploy_internlm2_5_7b_chat import \
models as hf_internlm2_5_7b_chat_model
# Summary Groups
from opencompass.configs.summarizers.groups.bbh import bbh_summary_groups
from opencompass.configs.summarizers.groups.mmlu_pro import \
mmlu_pro_summary_groups
#######################################################################
# PART 1 Datasets List #
#######################################################################
# datasets list for evaluation
# Only take LCB generation for evaluation
datasets = sum((v for k, v in locals().items() if k.endswith('_datasets')),
[]) + [LCBCodeGeneration_dataset]
# LLM judge config: using LLM to evaluate predictions
judge_cfg = dict()
for dataset in datasets:
dataset['infer_cfg']['inferencer']['max_out_len'] = 32768
if 'judge_cfg' in dataset['eval_cfg']['evaluator']:
dataset['eval_cfg']['evaluator']['judge_cfg'] = judge_cfg
#######################################################################
# PART 2 Datset Summarizer #
#######################################################################
core_summary_groups = [
{
'name':
'core_average',
'subsets': [
['IFEval', 'Prompt-level-strict-accuracy'],
['bbh', 'naive_average'],
['math_prm800k_500', 'accuracy'],
['aime2024', 'accuracy'],
['GPQA_diamond', 'accuracy'],
['mmlu_pro', 'naive_average'],
['openai_humaneval', 'humaneval_pass@1'],
['lcb_code_generation', 'pass@1'],
],
},
]
summarizer = dict(
dataset_abbrs=[
['core_average', 'naive_average'],
'',
'Instruction Following',
['IFEval', 'Prompt-level-strict-accuracy'],
'',
'General Reasoning',
['bbh', 'naive_average'],
['GPQA_diamond', 'accuracy'],
'',
'Math Calculation',
['math_prm800k_500', 'accuracy'],
['aime2024', 'accuracy'],
'',
'Knowledge',
['mmlu_pro', 'naive_average'],
'',
'Code',
['openai_humaneval', 'humaneval_pass@1'],
['lcb_code_generation', 'pass@1'],
],
summary_groups=sum(
[v for k, v in locals().items() if k.endswith('_summary_groups')], []),
)
#######################################################################
# PART 3 Models List #
#######################################################################
models = sum([v for k, v in locals().items() if k.endswith('_model')], [])
#######################################################################
# PART 4 Inference/Evaluation Configuaration #
#######################################################################
# Local Runner
infer = dict(
partitioner=dict(type=NumWorkerPartitioner, num_worker=8),
runner=dict(
type=LocalRunner,
max_num_workers=16,
retry=0, # Modify if needed
task=dict(type=OpenICLInferTask),
),
)
# eval with local runner
eval = dict(
partitioner=dict(type=NaivePartitioner, n=10),
runner=dict(type=LocalRunner,
max_num_workers=16,
task=dict(type=OpenICLEvalTask)),
)
#######################################################################
# PART 5 Utils Configuaration #
#######################################################################
work_dir = './outputs/oc_academic_202502'

98
opencompass/configs/datasets/aime2024/aime2024_0shot_nocot_genericllmeval_academic_gen.py Normal file
View File

@ -0,0 +1,98 @@
# flake8: noqa
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
from opencompass.evaluator import GenericLLMEvaluator
from opencompass.datasets.generic import generic_llmjudge_academic_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=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_academic_postprocess,
metric_name='accuracy'),
),
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',
)
]

189
opencompass/configs/datasets/bbh/bbh_0shot_nocot_academic_gen.py Normal file
View File

@ -0,0 +1,189 @@
# flake8: noqa
import os
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 BBHDataset
from opencompass.datasets.generic import generic_llmjudge_academic_postprocess
bbh_reader_cfg = dict(input_columns=['input'], output_column='target')
bbh_multiple_choice_sets = [
'temporal_sequences',
'disambiguation_qa',
'date_understanding',
'tracking_shuffled_objects_three_objects',
'penguins_in_a_table',
'geometric_shapes',
'snarks',
'ruin_names',
'tracking_shuffled_objects_seven_objects',
'tracking_shuffled_objects_five_objects',
'logical_deduction_three_objects',
'hyperbaton',
'logical_deduction_five_objects',
'logical_deduction_seven_objects',
'movie_recommendation',
'salient_translation_error_detection',
'reasoning_about_colored_objects',
]
bbh_free_form_sets = [
'multistep_arithmetic_two',
'navigate',
'dyck_languages',
'word_sorting',
'sports_understanding',
'boolean_expressions',
'object_counting',
'formal_fallacies',
'causal_judgement',
'web_of_lies',
]
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{input}\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()
bbh_sets = bbh_multiple_choice_sets + bbh_free_form_sets
# For zero shot inference in bbh
bbh_datasets = []
for _name in bbh_sets:
bbh_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(round=[
dict(
role='HUMAN',
prompt=f"Question: {{input}}\n You must give your final answer by starting with 'So the answer is' "
)
])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer, max_out_len=512))
bbh_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=BBHDataset,
name=_name,
path='opencompass/bbh',
reader_cfg=bbh_reader_cfg,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_academic_postprocess, metric_name='score'),
),
pred_role='BOT',
)
bbh_datasets.append(
dict(
type=BBHDataset,
path='opencompass/bbh',
name=_name,
abbr='bbh-' + _name,
reader_cfg=bbh_reader_cfg,
infer_cfg=bbh_infer_cfg.copy(),
eval_cfg=bbh_eval_cfg.copy())
)
# For original 3 shot inference in bbh
bbh_3_shot_datasets = []
for _name in bbh_sets:
with open(os.path.join(os.path.dirname(__file__), 'lib_prompt', f'{_name}.txt'), 'r') as f:
_hint = f.read()
bbh_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(round=[
dict(
role='HUMAN',
prompt=f"Follow the given examples and answer the question.\n{_hint}\n\nQ: {{input}}\nA: Let's think step by step."
)
])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer, max_out_len=512))
bbh_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=BBHDataset,
name=_name,
path='opencompass/bbh',
reader_cfg=bbh_reader_cfg,
),
judge_cfg=dict(),
dict_postprocessor=dict(type=generic_llmjudge_academic_postprocess, metric_name='score'),
),
pred_role='BOT',
)
bbh_3_shot_datasets.append(
dict(
type=BBHDataset,
path='opencompass/bbh',
name=_name,
abbr='bbh-' + _name,
reader_cfg=bbh_reader_cfg,
infer_cfg=bbh_infer_cfg.copy(),
eval_cfg=bbh_eval_cfg.copy()))

100
opencompass/configs/datasets/math/math_prm800k_500_0shot_cot_academic_gen.py Normal file
View File

@ -0,0 +1,100 @@
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.evaluator import GenericLLMEvaluator
from opencompass.datasets import generic_llmjudge_academic_postprocess
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}\nPlease reason step by step, and 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_academic_postprocess),
),
pred_role='BOT',
)
math_datasets = [
dict(
type=MATHDataset,
abbr='math_prm800k_500',
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',
)
]

14
opencompass/configs/models/deepseek/hf_deepseek_r1_distill_llama_70b.py Normal file
View File

@ -0,0 +1,14 @@
from opencompass.models import HuggingFacewithChatTemplate
from opencompass.utils.text_postprocessors import extract_non_reasoning_content
models = [
dict(
type=HuggingFacewithChatTemplate,
abbr='deepseek-r1-distill-llama-70b-hf',
path='deepseek-ai/DeepSeek-R1-Distill-Llama-70B',
max_out_len=16384,
batch_size=8,
run_cfg=dict(num_gpus=8),
pred_postprocessor=dict(type=extract_non_reasoning_content)
)
]

14
opencompass/configs/models/deepseek/hf_deepseek_r1_distill_llama_8b.py Normal file
View File

@ -0,0 +1,14 @@
from opencompass.models import HuggingFacewithChatTemplate
from opencompass.utils.text_postprocessors import extract_non_reasoning_content
models = [
dict(
type=HuggingFacewithChatTemplate,
abbr='deepseek-r1-distill-llama-8b-hf',
path='deepseek-ai/DeepSeek-R1-Distill-Llama-8B',
max_out_len=16384,
batch_size=8,
run_cfg=dict(num_gpus=1),
pred_postprocessor=dict(type=extract_non_reasoning_content)
)
]

14
opencompass/configs/models/deepseek/hf_deepseek_r1_distill_qwen_14b.py Normal file
View File

@ -0,0 +1,14 @@
from opencompass.models import HuggingFacewithChatTemplate
from opencompass.utils.text_postprocessors import extract_non_reasoning_content
models = [
dict(
type=HuggingFacewithChatTemplate,
abbr='deepseek-r1-distill-qwen-14b-hf',
path='deepseek-ai/DeepSeek-R1-Distill-Qwen-14B',
max_out_len=16384,
batch_size=16,
run_cfg=dict(num_gpus=4),
pred_postprocessor=dict(type=extract_non_reasoning_content)
)
]

14
opencompass/configs/models/deepseek/hf_deepseek_r1_distill_qwen_1_5b.py Normal file
View File

@ -0,0 +1,14 @@
from opencompass.models import HuggingFacewithChatTemplate
from opencompass.utils.text_postprocessors import extract_non_reasoning_content
models = [
dict(
type=HuggingFacewithChatTemplate,
abbr='deepseek-r1-distill-qwen-1.5b-hf',
path='deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B',
max_out_len=16384,
batch_size=8,
run_cfg=dict(num_gpus=1),
pred_postprocessor=dict(type=extract_non_reasoning_content)
)
]

14
opencompass/configs/models/deepseek/hf_deepseek_r1_distill_qwen_32b.py Normal file
View File

@ -0,0 +1,14 @@
from opencompass.models import HuggingFacewithChatTemplate
from opencompass.utils.text_postprocessors import extract_non_reasoning_content
models = [
dict(
type=HuggingFacewithChatTemplate,
abbr='deepseek-r1-distill-qwen-32b-hf',
path='deepseek-ai/DeepSeek-R1-Distill-Qwen-32B',
max_out_len=16384,
batch_size=8,
run_cfg=dict(num_gpus=4),
pred_postprocessor=dict(type=extract_non_reasoning_content)
)
]

14
opencompass/configs/models/deepseek/hf_deepseek_r1_distill_qwen_7b.py Normal file
View File

@ -0,0 +1,14 @@
from opencompass.models import HuggingFacewithChatTemplate
from opencompass.utils.text_postprocessors import extract_non_reasoning_content
models = [
dict(
type=HuggingFacewithChatTemplate,
abbr='deepseek-r1-distill-qwen-7b-hf',
path='deepseek-ai/DeepSeek-R1-Distill-Qwen-7B',
max_out_len=16384,
batch_size=8,
run_cfg=dict(num_gpus=1),
pred_postprocessor=dict(type=extract_non_reasoning_content)
)
]

20
opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_llama_70b.py Normal file
View File

@ -0,0 +1,20 @@
from opencompass.models import TurboMindModelwithChatTemplate
from opencompass.utils.text_postprocessors import extract_non_reasoning_content
models = [
dict(
type=TurboMindModelwithChatTemplate,
abbr='deepseek-r1-distill-llama-70b-turbomind',
path='deepseek-ai/DeepSeek-R1-Distill-Llama-70B',
engine_config=dict(session_len=32768, max_batch_size=8, tp=8),
gen_config=dict(top_k=1,
temperature=1e-6,
top_p=0.9,
max_new_tokens=32768),
max_seq_len=32768,
max_out_len=32768,
batch_size=8,
run_cfg=dict(num_gpus=8),
pred_postprocessor=dict(type=extract_non_reasoning_content)
)
]

20
opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_llama_8b.py Normal file
View File

@ -0,0 +1,20 @@
from opencompass.models import TurboMindModelwithChatTemplate
from opencompass.utils.text_postprocessors import extract_non_reasoning_content
models = [
dict(
type=TurboMindModelwithChatTemplate,
abbr='deepseek-r1-distill-llama-8b-turbomind',
path='deepseek-ai/DeepSeek-R1-Distill-Llama-8B',
engine_config=dict(session_len=32768, max_batch_size=8, tp=1),
gen_config=dict(top_k=1,
temperature=1e-6,
top_p=0.9,
max_new_tokens=32768),
max_seq_len=32768,
max_out_len=32768,
batch_size=8,
run_cfg=dict(num_gpus=1),
pred_postprocessor=dict(type=extract_non_reasoning_content)
)
]

20
opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_qwen_14b.py Normal file
View File

@ -0,0 +1,20 @@
from opencompass.models import TurboMindModelwithChatTemplate
from opencompass.utils.text_postprocessors import extract_non_reasoning_content
models = [
dict(
type=TurboMindModelwithChatTemplate,
abbr='deepseek-r1-distill-qwen-14b-turbomind',
path='deepseek-ai/DeepSeek-R1-Distill-Qwen-14B',
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=32768),
max_seq_len=32768,
max_out_len=32768,
batch_size=16,
run_cfg=dict(num_gpus=2),
pred_postprocessor=dict(type=extract_non_reasoning_content)
)
]

20
opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_qwen_1_5b.py Normal file
View File

@ -0,0 +1,20 @@
from opencompass.models import TurboMindModelwithChatTemplate
from opencompass.utils.text_postprocessors import extract_non_reasoning_content
models = [
dict(
type=TurboMindModelwithChatTemplate,
abbr='deepseek-r1-distill-qwen-1_5b-turbomind',
path='deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B',
engine_config=dict(session_len=32768, max_batch_size=16, tp=1),
gen_config=dict(top_k=1,
temperature=1e-6,
top_p=0.9,
max_new_tokens=32768),
max_seq_len=32768,
max_out_len=32768,
batch_size=16,
run_cfg=dict(num_gpus=1),
pred_postprocessor=dict(type=extract_non_reasoning_content)
)
]

20
opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_qwen_32b.py Normal file
View File

@ -0,0 +1,20 @@
from opencompass.models import TurboMindModelwithChatTemplate
from opencompass.utils.text_postprocessors import extract_non_reasoning_content
models = [
dict(
type=TurboMindModelwithChatTemplate,
abbr='deepseek-r1-distill-qwen-32b-turbomind',
path='deepseek-ai/DeepSeek-R1-Distill-Qwen-32B',
engine_config=dict(session_len=32768, max_batch_size=16, tp=4),
gen_config=dict(top_k=1,
temperature=1e-6,
top_p=0.9,
max_new_tokens=32768),
max_seq_len=32768,
max_out_len=32768,
batch_size=16,
run_cfg=dict(num_gpus=4),
pred_postprocessor=dict(type=extract_non_reasoning_content)
)
]

20
opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_qwen_7b.py Normal file
View File

@ -0,0 +1,20 @@
from opencompass.models import TurboMindModelwithChatTemplate
from opencompass.utils.text_postprocessors import extract_non_reasoning_content
models = [
dict(
type=TurboMindModelwithChatTemplate,
abbr='deepseek-r1-distill-qwen-7b-turbomind',
path='deepseek-ai/DeepSeek-R1-Distill-Qwen-7B',
engine_config=dict(session_len=32768, max_batch_size=8, tp=1),
gen_config=dict(top_k=1,
temperature=1e-6,
top_p=0.9,
max_new_tokens=32768),
max_seq_len=32768,
max_out_len=32768,
batch_size=8,
run_cfg=dict(num_gpus=1),
pred_postprocessor=dict(type=extract_non_reasoning_content)
)
]

29
opencompass/datasets/generic.py
View File

@ -1,7 +1,10 @@
import re
def get_final_results(judged_answers, references, origial_responses):
def get_final_results(judged_answers,
references,
origial_responses,
metric_name='accuracy'):
count = 0
is_correct_count = 0
is_incorrect_count = 0
@ -39,7 +42,7 @@ def get_final_results(judged_answers, references, origial_responses):
is_correct) > 0 else 0
result = {
# 'accuracy_given_attempted': accuracy_given_attempted,
'accuracy': accuracy_given_attempted * 100,
metric_name: accuracy_given_attempted * 100,
'f1': f1,
'details': details
}
@ -69,3 +72,25 @@ def generic_llmjudge_postprocess(
results = get_final_results(judged_answers, references, origial_responses)
results['details'] = output
return results
def generic_llmjudge_academic_postprocess(
output: dict,
output_path: str,
metric_name: str = 'accuracy',
) -> 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,
metric_name)
results['details'] = output
# For academic summarizer
results.pop('f1', None)
return results