mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
[Feature] Add Config for CoreBench (#1547)
* [Feature] Add Config for CoreBench * Update
This commit is contained in:
Songyang Zhang
GitHub
parent
17eefc0e1e
commit
fe84bbd9a0
138
configs/eval_corebench_2409_longcontext.py
Normal file
138
configs/eval_corebench_2409_longcontext.py
Normal file
@ -0,0 +1,138 @@
|
||||
import os.path as osp
|
||||
from copy import deepcopy
|
||||
|
||||
from mmengine.config import read_base
|
||||
from opencompass.models import (HuggingFacewithChatTemplate,
|
||||
TurboMindModelwithChatTemplate)
|
||||
from opencompass.partitioners import NaivePartitioner, NumWorkerPartitioner
|
||||
from opencompass.runners import DLCRunner, LocalRunner
|
||||
from opencompass.tasks import OpenICLEvalTask, OpenICLInferTask
|
||||
|
||||
|
||||
#######################################################################
|
||||
# PART 0 Essential Configs #
|
||||
#######################################################################
|
||||
with read_base():
|
||||
from opencompass.configs.datasets.longbench.longbench import \
|
||||
longbench_datasets
|
||||
from opencompass.configs.datasets.needlebench.needlebench_8k.needlebench_8k import \
|
||||
needlebench_datasets as needlebench_8k_datasets
|
||||
from opencompass.configs.datasets.needlebench.needlebench_32k.needlebench_32k import \
|
||||
needlebench_datasets as needlebench_32k_datasets
|
||||
from opencompass.configs.datasets.needlebench.needlebench_128k.needlebench_128k import \
|
||||
needlebench_datasets as needlebench_128k_datasets
|
||||
from opencompass.configs.datasets.ruler.ruler_8k_gen import \
|
||||
ruler_datasets as ruler_8k_datasets
|
||||
from opencompass.configs.datasets.ruler.ruler_32k_gen import \
|
||||
ruler_datasets as ruler_32k_datasets
|
||||
from opencompass.configs.datasets.ruler.ruler_128k_gen import \
|
||||
ruler_datasets as ruler_128k_datasets
|
||||
# Summary Groups
|
||||
from opencompass.configs.summarizers.groups.longbench import \
|
||||
longbench_summary_groups
|
||||
from opencompass.configs.summarizers.groups.ruler import \
|
||||
ruler_summary_groups
|
||||
from opencompass.configs.summarizers.needlebench import (
|
||||
needlebench_8k_summarizer, needlebench_32k_summarizer,
|
||||
needlebench_128k_summarizer)
|
||||
|
||||
# Instruct models
|
||||
from opencompass.configs.models.qwen.lmdeploy_qwen2_7b_instruct import \
|
||||
models as lmdeploy_qwen2_7b_instruct_model
|
||||
|
||||
from opencompass.configs.models.hf_internlm.lmdeploy_internlm2_5_7b_chat_1m import \
|
||||
models as lmdeploy_internlm2_5_7b_1m_chat_model
|
||||
from opencompass.configs.models.hf_llama.lmdeploy_llama3_1_8b_instruct import \
|
||||
models as llama3_1_8b_instruct_model
|
||||
|
||||
|
||||
#######################################################################
|
||||
# PART 1 Datasets List #
|
||||
#######################################################################
|
||||
# datasets list for evaluation
|
||||
datasets = sum((v for k, v in locals().items() if k.endswith('_datasets')), [])
|
||||
|
||||
|
||||
#######################################################################
|
||||
# PART 2 Datset Summarizer #
|
||||
#######################################################################
|
||||
needlebench_8k_summary_groups = needlebench_8k_summarizer['summary_groups']
|
||||
needlebench_32k_summary_groups = needlebench_32k_summarizer['summary_groups']
|
||||
needlebench_128k_summary_groups = needlebench_128k_summarizer['summary_groups']
|
||||
|
||||
# Instruct models summarizer
|
||||
summarizer = dict(
|
||||
dataset_abbrs=[
|
||||
['ruler_8k', 'naive_average'],
|
||||
['ruler_32k', 'naive_average'],
|
||||
['ruler_128k', 'naive_average'],
|
||||
['NeedleBench-Overall-Score-8K', 'weighted_average'],
|
||||
['NeedleBench-Overall-Score-32K', 'weighted_average'],
|
||||
['NeedleBench-Overall-Score-128K', 'weighted_average'],
|
||||
['longbench', 'naive_average'],
|
||||
['longbench_zh', 'naive_average'],
|
||||
['longbench_en', 'naive_average'],
|
||||
'',
|
||||
'longbench_single-document-qa',
|
||||
'longbench_multi-document-qa',
|
||||
'longbench_summarization',
|
||||
'longbench_few-shot-learning',
|
||||
'longbench_synthetic-tasks',
|
||||
'longbench_code-completion',
|
||||
],
|
||||
summary_groups=sum(
|
||||
[v for k, v in locals().items() if k.endswith('_summary_groups')], []),
|
||||
)
|
||||
|
||||
|
||||
#######################################################################
|
||||
# PART 3 Models List #
|
||||
#######################################################################
|
||||
|
||||
lmdeploy_qwen2_7b_instruct_model[0]['max_seq_len'] = 1048576
|
||||
lmdeploy_qwen2_7b_instruct_model[0]['engine_config']['session_len'] = 1048576
|
||||
lmdeploy_qwen2_7b_instruct_model[0]['engine_config']['tp'] = 4
|
||||
lmdeploy_qwen2_7b_instruct_model[0]['engine_config']['rope_scaling_factor'] = 4
|
||||
lmdeploy_qwen2_7b_instruct_model[0]['run_cfg']['num_gpus'] = 4
|
||||
|
||||
llama3_1_8b_instruct_model[0]['max_seq_len'] = 1048576
|
||||
llama3_1_8b_instruct_model[0]['engine_config']['session_len'] = 1048576
|
||||
llama3_1_8b_instruct_model[0]['engine_config']['tp'] = 4
|
||||
llama3_1_8b_instruct_model[0]['engine_config']['rope_scaling_factor'] = 4
|
||||
llama3_1_8b_instruct_model[0]['run_cfg']['num_gpus'] = 4
|
||||
|
||||
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 #
|
||||
#######################################################################
|
||||
base_exp_dir = 'outputs/corebench/'
|
||||
work_dir = osp.join(base_exp_dir, 'long_context')
|
||||
208
configs/eval_corebench_2409_objective.py
Normal file
208
configs/eval_corebench_2409_objective.py
Normal file
@ -0,0 +1,208 @@
|
||||
from mmengine.config import read_base
|
||||
import os.path as osp
|
||||
from opencompass.partitioners import NaivePartitioner, NumWorkerPartitioner
|
||||
from opencompass.runners import LocalRunner
|
||||
from opencompass.tasks import OpenICLInferTask, OpenICLEvalTask
|
||||
|
||||
|
||||
#######################################################################
|
||||
# PART 0 Essential Configs #
|
||||
#######################################################################
|
||||
with read_base():
|
||||
# Datasets Part
|
||||
## Core Set
|
||||
# ## Examination
|
||||
from opencompass.configs.datasets.mmlu.mmlu_openai_simple_evals_gen_b618ea import mmlu_datasets
|
||||
from opencompass.configs.datasets.mmlu_pro.mmlu_pro_0shot_cot_gen_08c1de import mmlu_pro_datasets
|
||||
from opencompass.configs.datasets.cmmlu.cmmlu_0shot_cot_gen_305931 import cmmlu_datasets
|
||||
|
||||
# ## Reasoning
|
||||
from opencompass.configs.datasets.bbh.bbh_gen_4a31fa import bbh_datasets
|
||||
# TODO: Add HellaSwag
|
||||
# TODO: Add DROP
|
||||
|
||||
# ## Math
|
||||
from opencompass.configs.datasets.math.math_0shot_gen_393424 import math_datasets
|
||||
# TODO: Add GSM8K
|
||||
# TODO: Add MathBench
|
||||
|
||||
# ## Scientific
|
||||
from opencompass.configs.datasets.gpqa.gpqa_openai_simple_evals_gen_5aeece import gpqa_datasets
|
||||
|
||||
# ## Coding
|
||||
from opencompass.configs.datasets.humaneval.humaneval_gen_8e312c import humaneval_datasets
|
||||
# TODO: Add MBPP
|
||||
# TODO: Add LiveCodeBench
|
||||
|
||||
# ## Instruction Following
|
||||
from opencompass.configs.datasets.IFEval.IFEval_gen_3321a3 import ifeval_datasets
|
||||
|
||||
# Summarizer
|
||||
from opencompass.configs.summarizers.groups.mmlu import mmlu_summary_groups
|
||||
from opencompass.configs.summarizers.groups.mmlu_pro import mmlu_pro_summary_groups
|
||||
from opencompass.configs.summarizers.groups.cmmlu import cmmlu_summary_groups
|
||||
from opencompass.configs.summarizers.groups.bbh import bbh_summary_groups
|
||||
|
||||
|
||||
# Model List
|
||||
# from opencompass.configs.models.qwen.lmdeploy_qwen2_1_5b_instruct import models as lmdeploy_qwen2_1_5b_instruct_model
|
||||
# from opencompass.configs.models.hf_internlm.lmdeploy_internlm2_5_7b_chat import models as hf_internlm2_5_7b_chat_model
|
||||
# from opencompass.configs.models.openbmb.hf_minicpm_2b_sft_bf16 import models as hf_minicpm_2b_sft_bf16_model
|
||||
# from opencompass.configs.models.yi.hf_yi_1_5_6b_chat import models as hf_yi_1_5_6b_chat_model
|
||||
# from opencompass.configs.models.gemma.hf_gemma_2b_it import models as hf_gemma_2b_it_model
|
||||
# from opencompass.configs.models.yi.hf_yi_1_5_34b_chat import models as hf_yi_1_5_34b_chat_model
|
||||
|
||||
#######################################################################
|
||||
# PART 1 Datasets List #
|
||||
#######################################################################
|
||||
# datasets list for evaluation
|
||||
datasets = sum((v for k, v in locals().items() if k.endswith('_datasets')), [])
|
||||
|
||||
|
||||
#######################################################################
|
||||
# PART 2 Datset Summarizer #
|
||||
#######################################################################
|
||||
# with read_base():
|
||||
|
||||
core_summary_groups = [
|
||||
{
|
||||
'name': 'core_average',
|
||||
'subsets': [
|
||||
['mmlu', 'accuracy'],
|
||||
['mmlu_pro', 'accuracy'],
|
||||
# ['cmmlu', 'naive_average'],
|
||||
['cmmlu', 'accuracy'],
|
||||
['bbh', 'score'],
|
||||
['math', 'accuracy'],
|
||||
['openai_humaneval', 'humaneval_pass@1'],
|
||||
['GPQA_diamond', 'accuracy'],
|
||||
['IFEval', 'Prompt-level-strict-accuracy'],
|
||||
],
|
||||
},
|
||||
]
|
||||
|
||||
summarizer = dict(
|
||||
dataset_abbrs=[
|
||||
['core_average', 'naive_average'],
|
||||
['mmlu', 'accuracy'],
|
||||
['mmlu_pro', 'accuracy'],
|
||||
['cmmlu', 'accuracy'],
|
||||
['bbh', 'score'],
|
||||
['math', 'accuracy'],
|
||||
['openai_humaneval', 'humaneval_pass@1'],
|
||||
['GPQA_diamond', 'accuracy'],
|
||||
['IFEval', 'Prompt-level-strict-accuracy'],
|
||||
'',
|
||||
|
||||
['mmlu', 'accuracy'],
|
||||
['mmlu-stem', 'accuracy'],
|
||||
['mmlu-social-science', 'accuracy'],
|
||||
['mmlu-humanities', 'accuracy'],
|
||||
['mmlu-other', 'accuracy'],
|
||||
|
||||
'',
|
||||
['mmlu_pro', 'accuracy'],
|
||||
['mmlu_pro_math','accuracy'],
|
||||
['mmlu_pro_physics', 'accuracy'],
|
||||
['mmlu_pro_chemistry', 'accuracy'],
|
||||
['mmlu_pro_law', 'accuracy'],
|
||||
['mmlu_pro_engineering', 'accuracy'],
|
||||
['mmlu_pro_other', 'accuracy'],
|
||||
['mmlu_pro_economics', 'accuracy'],
|
||||
['mmlu_pro_health', 'accuracy'],
|
||||
['mmlu_pro_psychology', 'accuracy'],
|
||||
['mmlu_pro_business', 'accuracy'],
|
||||
['mmlu_pro_biology', 'accuracy'],
|
||||
['mmlu_pro_philosophy', 'accuracy'],
|
||||
['mmlu_pro_computer_science','accuracy'],
|
||||
['mmlu_pro_history', 'accuracy'],
|
||||
'',
|
||||
['cmmlu', 'accuracy'],
|
||||
['cmmlu-stem', 'accuracy'],
|
||||
['cmmlu-social-science', 'accuracy'],
|
||||
['cmmlu-humanities', 'accuracy'],
|
||||
['cmmlu-other', 'accuracy'],
|
||||
['cmmlu-china-specific', 'accuracy'],
|
||||
'',
|
||||
['bbh', 'extract_rate'],
|
||||
['math', 'extract_rate'],
|
||||
# ['openai_humaneval', 'extract_rate'],
|
||||
['GPQA_diamond', 'extract_rate'],
|
||||
# ['IFEval', 'extract_rate'],
|
||||
'',
|
||||
['mmlu', 'extract_rate'],
|
||||
['mmlu-stem', 'extract_rate'],
|
||||
['mmlu-social-science', 'extract_rate'],
|
||||
['mmlu-humanities', 'extract_rate'],
|
||||
['mmlu-other', 'extract_rate'],
|
||||
'',
|
||||
['mmlu_pro', 'extract_rate'],
|
||||
['mmlu_pro_math', 'extract_rate'],
|
||||
['mmlu_pro_physics', 'extract_rate'],
|
||||
['mmlu_pro_chemistry', 'extract_rate'],
|
||||
['mmlu_pro_law', 'extract_rate'],
|
||||
['mmlu_pro_engineering', 'extract_rate'],
|
||||
['mmlu_pro_other', 'extract_rate'],
|
||||
['mmlu_pro_economics', 'extract_rate'],
|
||||
['mmlu_pro_health', 'extract_rate'],
|
||||
['mmlu_pro_psychology', 'extract_rate'],
|
||||
['mmlu_pro_business', 'extract_rate'],
|
||||
['mmlu_pro_biology', 'extract_rate'],
|
||||
['mmlu_pro_philosophy', 'extract_rate'],
|
||||
['mmlu_pro_computer_science', 'extract_rate'],
|
||||
['mmlu_pro_history', 'extract_rate'],
|
||||
'',
|
||||
['cmmlu', 'extract_rate'],
|
||||
['cmmlu-stem', 'extract_rate'],
|
||||
['cmmlu-social-science', 'extract_rate'],
|
||||
['cmmlu-humanities', 'extract_rate'],
|
||||
['cmmlu-other', 'extract_rate'],
|
||||
['cmmlu-china-specific', 'extract_rate'],
|
||||
|
||||
],
|
||||
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 #
|
||||
#######################################################################
|
||||
base_exp_dir = 'outputs/corebench/'
|
||||
work_dir = osp.join(base_exp_dir, 'chat_objective')
|
||||
134
configs/eval_corebench_2409_subjective.py
Normal file
134
configs/eval_corebench_2409_subjective.py
Normal file
@ -0,0 +1,134 @@
|
||||
import os.path as osp
|
||||
from copy import deepcopy
|
||||
|
||||
from mmengine.config import read_base
|
||||
from opencompass.models import (HuggingFacewithChatTemplate,
|
||||
TurboMindModelwithChatTemplate)
|
||||
from opencompass.models.openai_api import OpenAI, OpenAISDK
|
||||
from opencompass.partitioners import NaivePartitioner, NumWorkerPartitioner
|
||||
from opencompass.partitioners.sub_naive import SubjectiveNaivePartitioner
|
||||
from opencompass.runners import DLCRunner, LocalRunner
|
||||
from opencompass.summarizers import SubjectiveSummarizer
|
||||
from opencompass.tasks import OpenICLEvalTask, OpenICLInferTask
|
||||
from opencompass.tasks.subjective_eval import SubjectiveEvalTask
|
||||
|
||||
|
||||
#######################################################################
|
||||
# PART 0 Essential Configs #
|
||||
#######################################################################
|
||||
with read_base():
|
||||
# Datasets Part
|
||||
from opencompass.configs.datasets.subjective.arena_hard.arena_hard_compare import \
|
||||
arenahard_datasets
|
||||
from opencompass.configs.datasets.subjective.alignbench.alignbench_v1_1_judgeby_critiquellm import \
|
||||
alignbench_datasets
|
||||
from opencompass.configs.datasets.subjective.multiround.mtbench_single_judge_diff_temp import \
|
||||
mtbench_datasets
|
||||
|
||||
# Summarizer
|
||||
|
||||
# Model List
|
||||
# from opencompass.configs.models.qwen.lmdeploy_qwen2_1_5b_instruct import models as lmdeploy_qwen2_1_5b_instruct_model
|
||||
# from opencompass.configs.models.hf_internlm.lmdeploy_internlm2_5_7b_chat import models as hf_internlm2_5_7b_chat_model
|
||||
|
||||
|
||||
#######################################################################
|
||||
# PART 1 Datasets List #
|
||||
#######################################################################
|
||||
# datasets list for evaluation
|
||||
|
||||
datasets = sum((v for k, v in locals().items() if k.endswith('_datasets')), [])
|
||||
|
||||
|
||||
#######################################################################
|
||||
# PART 2 Datset Summarizer #
|
||||
#######################################################################
|
||||
summarizer = dict(type=SubjectiveSummarizer, function='subjective')
|
||||
|
||||
#######################################################################
|
||||
# PART 3 Models List #
|
||||
#######################################################################
|
||||
|
||||
models = [
|
||||
dict(
|
||||
type=TurboMindModelwithChatTemplate,
|
||||
abbr='internlm2_5-7b-chat-turbomind',
|
||||
path='internlm/internlm2_5-7b-chat',
|
||||
engine_config=dict(session_len=16384, max_batch_size=16, tp=1),
|
||||
gen_config=dict(top_k=40, temperature=1.0, top_p=0.9, max_new_tokens=4096),
|
||||
max_seq_len=16384,
|
||||
max_out_len=4096,
|
||||
batch_size=16,
|
||||
run_cfg=dict(num_gpus=1),
|
||||
)
|
||||
]
|
||||
|
||||
models = sum([v for k, v in locals().items() if k.endswith('_model')], models)
|
||||
|
||||
|
||||
|
||||
#######################################################################
|
||||
# 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)
|
||||
),
|
||||
)
|
||||
|
||||
# JudgeLLM
|
||||
api_meta_template = dict(round=[
|
||||
dict(role='HUMAN', api_role='HUMAN'),
|
||||
dict(role='BOT', api_role='BOT', generate=True),
|
||||
])
|
||||
|
||||
|
||||
judge_models = [
|
||||
dict(
|
||||
type=OpenAISDK,
|
||||
abbr='gpt-4o-2024-08-06',
|
||||
path='gpt-4o-2024-08-06',
|
||||
# openai_api_base=
|
||||
# 'http://10.140.1.86:10001/v1', # Change to your own url if needed.
|
||||
key='YOUR_API_KEY',
|
||||
retry=10,
|
||||
meta_template=api_meta_template,
|
||||
rpm_verbose=True,
|
||||
query_per_second=1,
|
||||
max_out_len=4096,
|
||||
max_seq_len=16384,
|
||||
batch_size=16,
|
||||
temperature=0.01,
|
||||
tokenizer_path='gpt-4o-2024-08-06'
|
||||
)
|
||||
]
|
||||
|
||||
# Evaluation with local runner
|
||||
eval = dict(
|
||||
partitioner=dict(
|
||||
type=SubjectiveNaivePartitioner,
|
||||
models=models,
|
||||
judge_models=judge_models,
|
||||
),
|
||||
runner=dict(
|
||||
type=LocalRunner,
|
||||
max_num_workers=16,
|
||||
task=dict(type=SubjectiveEvalTask)),
|
||||
)
|
||||
|
||||
|
||||
|
||||
#######################################################################
|
||||
# PART 5 Utils Configuaration #
|
||||
#######################################################################
|
||||
base_exp_dir = 'outputs/corebench/'
|
||||
work_dir = osp.join(base_exp_dir, 'chat_subjective')
|
||||
Loading…
Reference in New Issue
Block a user