diff --git a/examples/eval_academic_leaderboard_202502.py b/examples/eval_academic_leaderboard_202502.py new file mode 100644 index 00000000..231e9a9f --- /dev/null +++ b/examples/eval_academic_leaderboard_202502.py @@ -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' diff --git a/opencompass/configs/datasets/aime2024/aime2024_0shot_nocot_genericllmeval_academic_gen.py b/opencompass/configs/datasets/aime2024/aime2024_0shot_nocot_genericllmeval_academic_gen.py new file mode 100644 index 00000000..30da2b98 --- /dev/null +++ b/opencompass/configs/datasets/aime2024/aime2024_0shot_nocot_genericllmeval_academic_gen.py @@ -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. + + + : \n{question}\n\n\n + : \n{answer}\n\n\n + : \n{prediction}\n\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', + ) +] diff --git a/opencompass/configs/datasets/bbh/bbh_0shot_nocot_academic_gen.py b/opencompass/configs/datasets/bbh/bbh_0shot_nocot_academic_gen.py new file mode 100644 index 00000000..f0698689 --- /dev/null +++ b/opencompass/configs/datasets/bbh/bbh_0shot_nocot_academic_gen.py @@ -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. + + + : \n{input}\n\n\n + : \n{target}\n\n\n + : \n{prediction}\n\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())) diff --git a/opencompass/configs/datasets/math/math_prm800k_500_0shot_cot_academic_gen.py b/opencompass/configs/datasets/math/math_prm800k_500_0shot_cot_academic_gen.py new file mode 100644 index 00000000..c23bc136 --- /dev/null +++ b/opencompass/configs/datasets/math/math_prm800k_500_0shot_cot_academic_gen.py @@ -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. + + + : \n{problem}\n\n\n + : \n{solution}\n\n\n + : \n{prediction}\n\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', + ) +] diff --git a/opencompass/configs/models/deepseek/hf_deepseek_r1_distill_llama_70b.py b/opencompass/configs/models/deepseek/hf_deepseek_r1_distill_llama_70b.py new file mode 100644 index 00000000..15ac9f90 --- /dev/null +++ b/opencompass/configs/models/deepseek/hf_deepseek_r1_distill_llama_70b.py @@ -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) + ) +] diff --git a/opencompass/configs/models/deepseek/hf_deepseek_r1_distill_llama_8b.py b/opencompass/configs/models/deepseek/hf_deepseek_r1_distill_llama_8b.py new file mode 100644 index 00000000..937c8bb2 --- /dev/null +++ b/opencompass/configs/models/deepseek/hf_deepseek_r1_distill_llama_8b.py @@ -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) + ) +] diff --git a/opencompass/configs/models/deepseek/hf_deepseek_r1_distill_qwen_14b.py b/opencompass/configs/models/deepseek/hf_deepseek_r1_distill_qwen_14b.py new file mode 100644 index 00000000..d4c97023 --- /dev/null +++ b/opencompass/configs/models/deepseek/hf_deepseek_r1_distill_qwen_14b.py @@ -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) + ) +] diff --git a/opencompass/configs/models/deepseek/hf_deepseek_r1_distill_qwen_1_5b.py b/opencompass/configs/models/deepseek/hf_deepseek_r1_distill_qwen_1_5b.py new file mode 100644 index 00000000..aa12591e --- /dev/null +++ b/opencompass/configs/models/deepseek/hf_deepseek_r1_distill_qwen_1_5b.py @@ -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) + ) +] diff --git a/opencompass/configs/models/deepseek/hf_deepseek_r1_distill_qwen_32b.py b/opencompass/configs/models/deepseek/hf_deepseek_r1_distill_qwen_32b.py new file mode 100644 index 00000000..d62d8085 --- /dev/null +++ b/opencompass/configs/models/deepseek/hf_deepseek_r1_distill_qwen_32b.py @@ -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) + ) +] diff --git a/opencompass/configs/models/deepseek/hf_deepseek_r1_distill_qwen_7b.py b/opencompass/configs/models/deepseek/hf_deepseek_r1_distill_qwen_7b.py new file mode 100644 index 00000000..9898843a --- /dev/null +++ b/opencompass/configs/models/deepseek/hf_deepseek_r1_distill_qwen_7b.py @@ -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) + ) +] diff --git a/opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_llama_70b.py b/opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_llama_70b.py new file mode 100644 index 00000000..1471be9b --- /dev/null +++ b/opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_llama_70b.py @@ -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) + ) +] diff --git a/opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_llama_8b.py b/opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_llama_8b.py new file mode 100644 index 00000000..46b521f2 --- /dev/null +++ b/opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_llama_8b.py @@ -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) + ) +] diff --git a/opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_qwen_14b.py b/opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_qwen_14b.py new file mode 100644 index 00000000..401299cd --- /dev/null +++ b/opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_qwen_14b.py @@ -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) + ) +] diff --git a/opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_qwen_1_5b.py b/opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_qwen_1_5b.py new file mode 100644 index 00000000..d19ace4e --- /dev/null +++ b/opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_qwen_1_5b.py @@ -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) + ) +] diff --git a/opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_qwen_32b.py b/opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_qwen_32b.py new file mode 100644 index 00000000..2ddef1d4 --- /dev/null +++ b/opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_qwen_32b.py @@ -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) + ) +] diff --git a/opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_qwen_7b.py b/opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_qwen_7b.py new file mode 100644 index 00000000..69f9e50f --- /dev/null +++ b/opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_qwen_7b.py @@ -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) + ) +] diff --git a/opencompass/datasets/generic.py b/opencompass/datasets/generic.py index 867ba61f..28a37a02 100644 --- a/opencompass/datasets/generic.py +++ b/opencompass/datasets/generic.py @@ -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